📡 Embodied AI Radar具身智能雷达 Star3

Most of this project is curated by Claude. Drop a star to cheer Claude on!本项目大量由 Claude 整理维护,点个 Star 给克劳德大小姐鼓励一下!

★ Feed a star投喂 Star

Sim-to-Real & Simulators仿真与 Sim-to-Real

Physics simulators, GPU-parallel training and transfer to real robots.物理仿真器、GPU 并行训练与向真实机器人迁移。

Search this topic by robot type:按机器人形态搜索本主题: Robot arm机械臂 (10) · Dexterous hand灵巧手 (11) · Humanoid人形 (16) · Quadruped / legged四足 / 足式 (4) · Mobile robot移动机器人 (6) · Drone / aerial无人机 (4) · Autonomous driving自动驾驶 (2)

Curated精选 (104)

★★★ Must-read★★★ 必读 (1)

★★ Highly recommended★★ 强烈推荐 (3)

Paper论文 2021 · ETH Zurich, NVIDIA ★★

Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning

Thousands of parallel GPU environments train a quadruped walking policy in minutes; legged_gym became a standard starter.数千个 GPU 并行环境几分钟就能训练出四足行走策略;legged_gym 成为标准入门框架。

BibTeX
@misc{rudin2021learning,
  title = {{Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning}},
  author = {Nikita Rudin and David Hoeller and Philipp Reist and Marco Hutter},
  year = {2021},
  eprint = {2109.11978},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2109.11978},
}
Paper论文 2026 · Apple ★★ new新 2026-11-05

Perceptive Humanoid Motion from Simulation

HALO trains humanoid skills on vision-language-motion data synthesised in a thousand procedural homes, so data scales with compute. Reports zero-shot transfer: 91% over 360 trials in six real environments.HALO 在上千个程序化生成的家庭场景中合成视觉-语言-动作数据来训练人形技能,数据量随算力增长。报告零微调迁移:六个未建图真实环境的 360 次试验成功率 91%。

BibTeX
@misc{hu2026perceptive,
  title = {{Perceptive Humanoid Motion from Simulation}},
  author = {Siyuan Hu and Abulikemu Abuduweili and Yue Meng and Shipeng Liu and Quentin Leboutet and Chen Chen and Matthias Müller and Vladlen Koltun},
  year = {2026},
  eprint = {2611.06908},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.06908},
}
Paper论文 2026 ★★ new新 2026-11-02

When the Simulator Fails, Not the Policy: Auditing Contact Artifacts in Simulated Robot Benchmarks

Many benchmark 'policy failures' are physics-engine ejections. SimuGuard traced RoboTwin artifacts to one collision constant; changing it cut artifact episodes from 12/100 to none and lifted five tasks 89% → 98%.审计仿真基准:不少“策略失败”其实是物理引擎把物体弹飞。SimuGuard 为 LIBERO、RoboTwin、RoboCasa、RoboDojo 提供审计插件,把 RoboTwin 上的问题追溯到碰撞检测的一个常量;仅改动它,异常回合由 100 回合 12 次降到 0,五个容器任务成功率由 89% 升到 98%。

BibTeX
@misc{zhou2026when,
  title = {{When the Simulator Fails, Not the Policy: Auditing Contact Artifacts in Simulated Robot Benchmarks}},
  author = {Alex Zhou and Junhao Wu and Xueyang Zhou and Yixiao Huo and Hongcheng Gao and Di Zhu and Zhenghao Zhang and Yongchao Chen},
  year = {2026},
  eprint = {2610.41857},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.41857},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realbenchmark-auditphysxrobotwinliberocontact

★ Recommended★ 推荐 (24)

Paper论文 2026 · NVIDIA ★ new新 2026-11-05

Interactive World Simulation with Cosmos for Physical AI

Adapts Cosmos models for real-time interactive simulation: streams observations in response to actions, or renders them from an external simulator's state. Shown on manipulation, video transfer and multi-view AV.将 Cosmos 模型用于实时交互仿真的统一框架:根据动作流式生成观测,或依据外部仿真器的物理状态生成观测。示例涵盖操作、可控视频迁移和多视角自动驾驶。

BibTeX
@misc{nvidia2026interactive,
  title = {{Interactive World Simulation with Cosmos for Physical AI}},
  author = {NVIDIA and : and Anis Ahmad and Jon Allen and Malik Aqeel Anwar and Jesse Archer and Maciej Bala and Piotr Barejko and Aarti Basant and Dan Blick and Taras Bolzhelarskyi and Henry Che and Jin Chen and Yukang Chen and Tae Eun Choe and Yuzhu Dong and Nat Duca and Liang Feng and Francesco Ferroni and Xiao Fu and Mohit Gambhir and Vivek Goel and Rony Goldenthal and Aryaman Gupta and Ali Hassani and Nathan Hayes-Roth and Yong He and Michael Honke and Shengyu Huang and Wei Huang and DeLesley Hutchins and Suneel Indupuru and Pooya Jannaty and Jingyi Jin and Janmesh Kalra and Ashna Khetan and Xin Kong and Aleksandr Korovko and Hui Kuang and Zhengfei Kuang and George Kurian and Jean-Francois Lafleche and Jayjun Lee and Justin Leung and William Lew and Xiang Li and Zhaoshuo Li and Chen-Hsuan Lin and Ming-Yu Liu and Xiangyu Lu and others},
  year = {2026},
  eprint = {2611.06627},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2611.06627},
}
World Models世界模型Sim-to-Real & Simulators仿真与 Sim-to-Realworld-foundation-modelreal-timevideosimulation
Paper论文 2026 ★ new新 2026-11-04

Genie Sim 3.0 : A High-Fidelity Comprehensive Simulation Platform for Humanoid Robot

Genie Sim 3.0: a manipulation simulation platform whose LLM tool builds scenes from natural language, with an LLM- and VLM-based automated benchmark.Genie Sim 3.0:面向操作的仿真平台,用 LLM 工具依自然语言生成场景,并提供基于 LLM 与 VLM 的自动化评测基准。

BibTeX
@misc{yin2026genie,
  title = {{Genie Sim 3.0 : A High-Fidelity Comprehensive Simulation Platform for Humanoid Robot}},
  author = {Chenghao Yin and Da Huang and Di Yang and Jichao Wang and Nanshu Zhao and Chen Xu and Wenjun Sun and Linjie Hou and Zhijun Li and Junhui Wu and Zhaobo Liu and Zhen Xiao and Sheng Zhang and Lei Bao and Rui Feng and Zhenquan Pang and Jiayu Li and Qian Wang and Maoqing Yao},
  year = {2026},
  eprint = {2601.02078},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2601.02078},
}
Sim-to-Real & Simulators仿真与 Sim-to-RealHumanoid人形simulatorhumanoidbenchmark
Paper论文 2025 · NVIDIA ★ new新 2026-11-04

World Simulation with Video Foundation Models for Physical AI

A flow-based world foundation model unifying Text2World, Image2World and Video2World, released at 2B and 14B, with Cosmos-Transfer2.5 for Sim2Real translation.基于流的世界基础模型,统一 Text2World、Image2World 和 Video2World,发布 2B 和 14B 两种规模,并配有用于 Sim2Real 转换的 Cosmos-Transfer2.5。

BibTeX
@misc{nvidia2025world,
  title = {{World Simulation with Video Foundation Models for Physical AI}},
  author = {NVIDIA and : and Arslan Ali and Junjie Bai and Maciej Bala and Yogesh Balaji and Aaron Blakeman and Tiffany Cai and Jiaxin Cao and Tianshi Cao and Elizabeth Cha and Yu-Wei Chao and Prithvijit Chattopadhyay and Mike Chen and Yongxin Chen and Yu Chen and Shuai Cheng and Yin Cui and Jenna Diamond and Yifan Ding and Jiaojiao Fan and Linxi Fan and Liang Feng and Francesco Ferroni and Sanja Fidler and Xiao Fu and Ruiyuan Gao and Yunhao Ge and Jinwei Gu and Aryaman Gupta and Siddharth Gururani and Imad El Hanafi and Ali Hassani and Zekun Hao and Jacob Huffman and Joel Jang and Pooya Jannaty and Jan Kautz and Grace Lam and Xuan Li and Zhaoshuo Li and Maosheng Liao and Chen-Hsuan Lin and Tsung-Yi Lin and Yen-Chen Lin and Huan Ling and Ming-Yu Liu and Xian Liu and Yifan Lu and Alice Luo and others},
  year = {2025},
  eprint = {2511.00062},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2511.00062},
}
Paper论文 2025 · Google DeepMind, UC Berkeley ★

MuJoCo Playground

GPU-accelerated MJX environments for locomotion and manipulation that train in minutes and transfer to real robots.基于 MJX 的 GPU 加速运动与操作环境,几分钟即可训练并迁移到真实机器人。

BibTeX
@misc{zakka2025mujoco,
  title = {{MuJoCo Playground}},
  author = {Kevin Zakka and Baruch Tabanpour and Qiayuan Liao and Mustafa Haiderbhai and Samuel Holt and Jing Yuan Luo and Arthur Allshire and Erik Frey and Koushil Sreenath and Lueder A. Kahrs and Carmelo Sferrazza and Yuval Tassa and Pieter Abbeel},
  year = {2025},
  eprint = {2502.08844},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2502.08844},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realgpu-parallelsim2realopen-source
Paper论文 2025 ★

RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation

Simulation pipeline that writes and checks task code with multimodal LLMs to mass-produce bimanual demos under heavy randomization (clutter, lighting, backgrounds, instructions); also a 50-task dual-arm benchmark.用多模态大模型自动生成并校验任务代码,在强域随机化(杂物、光照、背景、指令)下批量产出双臂演示数据的仿真管线,同时提供 50 个双臂任务的基准。

BibTeX
@misc{chen2025robotwin,
  title = {{RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation}},
  author = {Tianxing Chen and Zanxin Chen and Baijun Chen and Zijian Cai and Yibin Liu and Zixuan Li and Qiwei Liang and Xianliang Lin and Yiheng Ge and Zhenyu Gu and Weiliang Deng and Yubin Guo and Tian Nian and Xuanbing Xie and Qiangyu Chen and Kailun Su and Tianling Xu and Guodong Liu and Mengkang Hu and Huan-ang Gao and Kaixuan Wang and Zhixuan Liang and Yusen Qin and Xiaokang Yang and Ping Luo and Yao Mu},
  year = {2025},
  eprint = {2506.18088},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2506.18088},
}
Paper论文 2025 · NVIDIA ★

Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning

The reference paper for Isaac Lab, Orbit's successor — GPU-parallel physics, rendering and sensor simulation with ready-made robots and tasks for RL and imitation.Isaac Lab(Orbit 的后继)的正式论文:GPU 并行的物理、渲染与传感器仿真,内置机器人与任务,面向强化学习和模仿学习。

BibTeX
@misc{nvidia2025isaac,
  title = {{Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning}},
  author = {NVIDIA and : and Mayank Mittal and Pascal Roth and James Tigue and Antoine Richard and Octi Zhang and Peter Du and Antonio Serrano-Muñoz and Xinjie Yao and René Zurbrügg and Nikita Rudin and Lukasz Wawrzyniak and Milad Rakhsha and Alain Denzler and Eric Heiden and Ales Borovicka and Ossama Ahmed and Iretiayo Akinola and Abrar Anwar and Mark T. Carlson and Ji Yuan Feng and Animesh Garg and Renato Gasoto and Lionel Gulich and Yijie Guo and M. Gussert and Alex Hansen and Mihir Kulkarni and Chenran Li and Wei Liu and Viktor Makoviychuk and Grzegorz Malczyk and Hammad Mazhar and Masoud Moghani and Adithyavairavan Murali and Michael Noseworthy and Alexander Poddubny and Nathan Ratliff and Welf Rehberg and Clemens Schwarke and Ritvik Singh and James Latham Smith and Bingjie Tang and Ruchik Thaker and Matthew Trepte and Karl Van Wyk and Fangzhou Yu and Alex Millane and Vikram Ramasamy and others},
  year = {2025},
  eprint = {2511.04831},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2511.04831},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realgpu-parallelframeworksensorsopen-source
Simulator仿真器 2025 · Disney Research, Google DeepMind, NVIDIA (Linux Foundation project) ★

Newton

Open, GPU-accelerated physics engine built on NVIDIA Warp and OpenUSD with multiple solvers for contact-rich robot learning; co-developed by Disney Research, Google DeepMind and NVIDIA, hosted by the Linux Foundation.基于 NVIDIA Warp 和 OpenUSD 的开源 GPU 物理引擎,支持多种求解器,面向接触丰富的机器人学习;由 Disney Research、Google DeepMind 和 NVIDIA 联合开发,由 Linux 基金会托管。

Sim-to-Real & Simulators仿真与 Sim-to-Realphysicsgpu-parallelopen-sourcewarpopenusd
Benchmark基准 2025 · UC Berkeley · PKU · BIGAI · Stanford · CMU and others RSS 2025 ★

RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning

MetaSim puts many simulators (Isaac Sim/Gym, MuJoCo, Genesis, SAPIEN…) behind one interface; adds a large synthetic dataset migrated from public benchmarks and unified IL/RL benchmarks.MetaSim 用统一接口封装多种仿真器(Isaac Sim/Gym、MuJoCo、Genesis、SAPIEN、PyBullet 等);提供由公开基准迁移而来的大规模合成数据集,以及按泛化层级划分的统一模仿学习/强化学习基准。

BibTeX
@misc{geng2025roboverse,
  title = {{RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning}},
  author = {Haoran Geng and Feishi Wang and Songlin Wei and Yuyang Li and Bangjun Wang and Boshi An and Charlie Tianyue Cheng and Haozhe Lou and Peihao Li and Yen-Jen Wang and Yutong Liang and Dylan Goetting and Chaoyi Xu and Haozhe Chen and Yuxi Qian and Yiran Geng and Jiageng Mao and Weikang Wan and Mingtong Zhang and Jiangran Lyu and Siheng Zhao and Jiazhao Zhang and Jialiang Zhang and Chengyang Zhao and Haoran Lu and Yufei Ding and Ran Gong and Yuran Wang and Yuxuan Kuang and Ruihai Wu and Baoxiong Jia and Carlo Sferrazza and Hao Dong and Siyuan Huang and Yue Wang and Jitendra Malik and Pieter Abbeel},
  year = {2025},
  eprint = {2504.18904},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2504.18904},
}
Paper论文 2024 · UC San Diego ★

ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI

GPU-parallel simulation and rendering with many manipulation tasks; fast visual RL and data generation.GPU 并行仿真与渲染,内置大量操作任务,适合快速视觉强化学习与数据生成。

BibTeX
@misc{tao2024maniskill,
  title = {{ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI}},
  author = {Stone Tao and Fanbo Xiang and Arth Shukla and Yuzhe Qin and Xander Hinrichsen and Xiaodi Yuan and Chen Bao and Xinsong Lin and Yulin Liu and Tse-kai Chan and Yuan Gao and Xuanlin Li and Tongzhou Mu and Nan Xiao and Arnav Gurha and Viswesh Nagaswamy Rajesh and Yong Woo Choi and Yen-Ru Chen and Zhiao Huang and Roberto Calandra and Rui Chen and Shan Luo and Hao Su},
  year = {2024},
  eprint = {2410.00425},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2410.00425},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realgpu-parallelrenderingbenchmarkopen-source
Simulator仿真器 2024 · Genesis Embodied AI ★

Genesis

An open-source, Python-native physics platform covering rigid bodies, soft bodies, fluids and fast GPU simulation.开源、Python 原生的物理平台,覆盖刚体、软体、流体,支持高速 GPU 仿真。

Sim-to-Real & Simulators仿真与 Sim-to-Realphysicsgpu-parallelopen-source
Paper论文 2024 · UT Austin, NVIDIA ★

RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots

120 kitchen scenes, 2,500+ objects and 100 tasks with generated demonstrations for training generalist policies.120 个厨房场景、2500 多个物体与 100 个任务,并附生成演示,用于训练通用策略。

BibTeX
@misc{nasiriany2024robocasa,
  title = {{RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots}},
  author = {Soroush Nasiriany and Abhiram Maddukuri and Lance Zhang and Adeet Parikh and Aaron Lo and Abhishek Joshi and Ajay Mandlekar and Yuke Zhu},
  year = {2024},
  eprint = {2406.02523},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2406.02523},
}
Paper论文 2024 · RobotEra ★

Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer

Isaac Gym–based RL framework for humanoid locomotion with a sim-to-sim check in MuJoCo before deploying zero-shot to real humanoids; a common starting point for humanoid RL.基于 Isaac Gym 的人形机器人运动强化学习框架,先在 MuJoCo 中做 sim2sim 验证,再零样本部署到真实人形机器人,是人形 RL 的常用起点。

BibTeX
@misc{gu2024humanoid,
  title = {{Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer}},
  author = {Xinyang Gu and Yen-Jen Wang and Jianyu Chen},
  year = {2024},
  eprint = {2404.05695},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2404.05695},
}
Simulator仿真器 2024 · OpenRobotLab ★ new新 2026-11-04

GRUtopia: Dream General Robots in a City at Scale

Simulated interactive 3D society for many robot types; its GRScenes set has 100k annotated scenes across 89 categories that combine into city-scale worlds.面向多种机器人的交互式三维仿真社会;GRScenes 含 10 万标注场景、89 个类别,可组合成城市级环境。

BibTeX
@misc{wang2024grutopia,
  title = {{GRUtopia: Dream General Robots in a City at Scale}},
  author = {Hanqing Wang and Jiahe Chen and Wensi Huang and Qingwei Ben and Tai Wang and Boyu Mi and Tao Huang and Siheng Zhao and Yilun Chen and Sizhe Yang and Peizhou Cao and Wenye Yu and Zichao Ye and Jialun Li and Junfeng Long and Zirui Wang and Huiling Wang and Ying Zhao and Zhongying Tu and Yu Qiao and Dahua Lin and Jiangmiao Pang},
  year = {2024},
  eprint = {2407.10943},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2407.10943},
}
Paper论文 2023 · ETH Zurich, NVIDIA, Toronto ★

Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments

The framework that became Isaac Lab — modular robots, sensors and tasks on top of Isaac Sim.Isaac Lab 的前身,在 Isaac Sim 之上提供模块化的机器人、传感器与任务。

BibTeX
@misc{mittal2023orbit,
  title = {{Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments}},
  author = {Mayank Mittal and Calvin Yu and Qinxi Yu and Jingzhou Liu and Nikita Rudin and David Hoeller and Jia Lin Yuan and Ritvik Singh and Yunrong Guo and Hammad Mazhar and Ajay Mandlekar and Buck Babich and Gavriel State and Marco Hutter and Animesh Garg},
  year = {2023},
  eprint = {2301.04195},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2301.04195},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realgpu-parallelframeworkopen-source
Paper论文 2023 · Meta AI ICLR 2024 ★

Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots

Adds simulated humanoid avatars and a human-in-the-loop interface to Habitat, so robots can be trained and evaluated on tasks shared with people, such as social navigation and social rearrangement.为 Habitat 加入仿真人形化身和真人在环交互接口,可在与人协作的任务(如社交导航、社交重排)上训练和评测机器人。

BibTeX
@misc{puig2023habitat,
  title = {{Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots}},
  author = {Xavier Puig and Eric Undersander and Andrew Szot and Mikael Dallaire Cote and Tsung-Yen Yang and Ruslan Partsey and Ruta Desai and Alexander William Clegg and Michal Hlavac and So Yeon Min and Vladimír Vondruš and Theophile Gervet and Vincent-Pierre Berges and John M. Turner and Oleksandr Maksymets and Zsolt Kira and Mrinal Kalakrishnan and Jitendra Malik and Devendra Singh Chaplot and Unnat Jain and Dhruv Batra and Akshara Rai and Roozbeh Mottaghi},
  year = {2023},
  eprint = {2310.13724},
  archivePrefix = {arXiv},
  primaryClass = {cs.HC},
  url = {https://arxiv.org/abs/2310.13724},
}
Sim-to-Real & Simulators仿真与 Sim-to-RealNavigation & Embodied Agents导航与具身智能体Humanoid人形simhuman-robot-collaborationhumanoid-avatarssocial-navigation
Paper论文 2023 ICLR 2023 ★

ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills

Unified manipulation benchmark built to add object-level geometric and topological variation that earlier suites lacked.统一的操作基准,补上早期环境缺少的物体级几何与拓扑变化。

BibTeX
@misc{gu2023maniskill,
  title = {{ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills}},
  author = {Jiayuan Gu and Fanbo Xiang and Xuanlin Li and Zhan Ling and Xiqiang Liu and Tongzhou Mu and Yihe Tang and Stone Tao and Xinyue Wei and Yunchao Yao and Xiaodi Yuan and Pengwei Xie and Zhiao Huang and Rui Chen and Hao Su},
  year = {2023},
  eprint = {2302.04659},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2302.04659},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realbenchmarksimulatorgeneralization
Paper论文 2022 · Stanford CoRL 2022 ★

BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation

1,000 household activities chosen from a survey of what people want robots to do, defined in a logic language and simulated in OmniGibson with realistic physics and rendering.依据人们希望机器人做什么的调查挑选出 1000 项家务活动,用逻辑语言定义,并在具备真实物理与渲染的 OmniGibson 中仿真。

BibTeX
@misc{li2024behavior,
  title = {{BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation}},
  author = {Chengshu Li and Ruohan Zhang and Josiah Wong and Cem Gokmen and Sanjana Srivastava and Roberto Martín-Martín and Chen Wang and Gabrael Levine and Wensi Ai and Benjamin Martinez and Hang Yin and Michael Lingelbach and Minjune Hwang and Ayano Hiranaka and Sujay Garlanka and Arman Aydin and Sharon Lee and Jiankai Sun and Mona Anvari and Manasi Sharma and Dhruva Bansal and Samuel Hunter and Kyu-Young Kim and Alan Lou and Caleb R Matthews and Ivan Villa-Renteria and Jerry Huayang Tang and Claire Tang and Fei Xia and Yunzhu Li and Silvio Savarese and Hyowon Gweon and C. Karen Liu and Jiajun Wu and Li Fei-Fei},
  year = {2024},
  eprint = {2403.09227},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2403.09227},
}
Paper论文 2021 · Google NeurIPS 2021 Datasets and Benchmarks ★

Brax: A Differentiable Physics Engine for Large Scale Rigid Body Simulation

JAX physics engine that runs thousands of environments in parallel on GPU/TPU together with the RL training loop, cutting locomotion training from hours to minutes.基于 JAX 的物理引擎,在 GPU/TPU 上与强化学习训练循环一起并行运行数千个环境,把运动控制训练从数小时缩短到数分钟。

BibTeX
@misc{freeman2021brax,
  title = {{Brax: A Differentiable Physics Engine for Large Scale Rigid Body Simulation}},
  author = {C. Daniel Freeman and Erik Frey and Anton Raichuk and Sertan Girgin and Igor Mordatch and Olivier Bachem},
  year = {2021},
  eprint = {2106.13281},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2106.13281},
}
Paper论文 2020 · Stanford, UT Austin ★

robosuite: A Modular Simulation Framework and Benchmark for Robot Learning

Modular MuJoCo-based manipulation environments behind many imitation-learning benchmarks.基于 MuJoCo 的模块化操作环境,是众多模仿学习基准的底座。

BibTeX
@misc{zhu2020robosuite,
  title = {{robosuite: A Modular Simulation Framework and Benchmark for Robot Learning}},
  author = {Yuke Zhu and Josiah Wong and Ajay Mandlekar and Roberto Martín-Martín and Abhishek Joshi and Kevin Lin and Abhiram Maddukuri and Soroush Nasiriany and Yifeng Zhu},
  year = {2020},
  eprint = {2009.12293},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2009.12293},
}
Paper论文 2020 · DeepMind ★

dm_control: Software and Tasks for Continuous Control

DeepMind's Python stack on top of MuJoCo — bindings, PyMJCF and Composer for building models and tasks, the standard Control Suite benchmarks, plus locomotion and arm-and-bricks manipulation tasks.DeepMind 基于 MuJoCo 的 Python 工具栈:底层绑定、用于程序化建模与编写任务的 PyMJCF 和 Composer、作为标准基准的 Control Suite,以及运动控制和机械臂拼积木操作任务。

BibTeX
@misc{tassa2020dm,
  title = {{dm_control: Software and Tasks for Continuous Control}},
  author = {Yuval Tassa and Saran Tunyasuvunakool and Alistair Muldal and Yotam Doron and Piotr Trochim and Siqi Liu and Steven Bohez and Josh Merel and Tom Erez and Timothy Lillicrap and Nicolas Heess},
  year = {2020},
  eprint = {2006.12983},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2006.12983},
}
Paper论文 2019 · Meta AI ★

Habitat: A Platform for Embodied AI Research

A very fast photorealistic 3D simulator and task suite that standardized embodied navigation research.极速的逼真 3D 仿真器与任务集,统一了具身导航研究的标准。

BibTeX
@misc{savva2019habitat,
  title = {{Habitat: A Platform for Embodied AI Research}},
  author = {Manolis Savva and Abhishek Kadian and Oleksandr Maksymets and Yili Zhao and Erik Wijmans and Bhavana Jain and Julian Straub and Jia Liu and Vladlen Koltun and Jitendra Malik and Devi Parikh and Dhruv Batra},
  year = {2019},
  eprint = {1904.01201},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/1904.01201},
}
Paper论文 2017 · Allen Institute for AI ★

AI2-THOR: An Interactive 3D Environment for Visual AI

Photorealistic interactive indoor scenes where agents open, pick up and change objects; the base of many embodied-AI benchmarks such as ALFRED.具有可交互物体的逼真室内场景,智能体可开关、拾取和改变物体,是 ALFRED 等众多具身智能基准的基础。

BibTeX
@misc{kolve2017ai,
  title = {{AI2-THOR: An Interactive 3D Environment for Visual AI}},
  author = {Eric Kolve and Roozbeh Mottaghi and Winson Han and Eli VanderBilt and Luca Weihs and Alvaro Herrasti and Matt Deitke and Kiana Ehsani and Daniel Gordon and Yuke Zhu and Aniruddha Kembhavi and Abhinav Gupta and Ali Farhadi},
  year = {2017},
  eprint = {1712.05474},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/1712.05474},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realhouseholdinteractiveembodied-agentsopen-source
Code代码 2014 · MIT, Toyota Research Institute ★

Drake

Model-based toolbox for robotics - multibody dynamics with contact simulation, mathematical programming and trajectory optimization; used in the MIT manipulation and underactuated courses.面向机器人的基于模型的工具箱:带接触的多体动力学仿真、数学规划与轨迹优化;MIT 操作与欠驱动课程即使用它。

Simulator仿真器 2004 · Open Robotics ★

Gazebo

The long-standing open-source robot simulator of the ROS ecosystem — sensors, plugins and ROS 2 integration; the usual choice for testing full robot software stacks rather than training policies.ROS 生态中历史悠久的开源机器人仿真器,提供传感器、插件与 ROS 2 集成;通常用于测试完整的机器人软件栈,而非训练策略。

More更多 (76)

Paper论文 2026 · MIT new新 2026-10-19

Blind Precise Assembly: Proprioceptive Sim-to-Real Peg-in-Hole for Diverse Parts

Asks whether joint readings alone suffice for millimetre-precise insertion — trains sim-to-real policies with no camera, force or tactile input.探究仅靠关节读数能否完成毫米级精密插装:训练不用相机、力或触觉输入的 sim-to-real 策略。

BibTeX
@misc{bronars2026blind,
  title = {{Blind Precise Assembly: Proprioceptive Sim-to-Real Peg-in-Hole for Diverse Parts}},
  author = {Antonia Bronars and Younghyo Park and Kushal Kedia and Pulkit Agrawal},
  year = {2026},
  eprint = {2610.23849},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.23849},
}
Paper论文 2026 new新 2026-10-28

Dexterous In-Hand Object Pose Reaching with Learned Safety Filters

Sim-only RL recipe for in-hand object pose reaching on a LEAP hand, zero-shot to hardware; reports 95.2% of 4,800 unseen goals reached and a tunable residual safety filter that cuts drops by 75%.在仿真中无需人类数据训练 LEAP 灵巧手的手内物体位姿到达策略,零样本迁移到真机;报告在 4800 个未见目标上 95.2% 到达,可调节的残差安全滤波器使掉落减少 75%。

BibTeX
@misc{chuang2026dexterous,
  title = {{Dexterous In-Hand Object Pose Reaching with Learned Safety Filters}},
  author = {Ian Chuang and Hiya Shah and Vamsi Chilamkur and Iman Soltani and Claire Tomlin},
  year = {2026},
  eprint = {2610.37652},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.37652},
}
Paper论文 2026 new新 2026-11-03

BeyondContact: A Reinforcement Learning Framework for Airflow-Based Non-Contact Manipulation

Airflow extension for Isaac Lab with experimentally identified models, plus a light blower beside the gripper. Reports zero-shot real push-and-blow at 80% over 20 trials and 2.6° heading error with air alone.为 Isaac Lab 增加基于实测模型的气流扩展,并在夹爪旁加装轻型鼓风机。报告零调试真机部署:推吹混合策略 20 次成功率 80%,纯气流转向平均误差 2.6°。

BibTeX
@misc{yang2026beyondcontact,
  title = {{BeyondContact: A Reinforcement Learning Framework for Airflow-Based Non-Contact Manipulation}},
  author = {Peiyu Yang and Mohamad S. Moudallal and Antonio Langella and Giulio Turrisi and Victor Barasuol and Claudio Semini},
  year = {2026},
  eprint = {2611.03059},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.03059},
}
Paper论文 2026 CoRL 2026 Spotlight new新 2026-11-04

Robustness without Wrinkles: Parallel Simulation and Robust MPC for Certified Deformable Manipulation

CORD-SLS pairs a GPU-parallel differentiable simulator with robust MPC and conformal bounds for rope and cloth, reporting millisecond planning with safety margins on hardware.CORD-SLS 将 GPU 并行可微仿真与鲁棒 MPC、共形预测误差界结合,用于绳索和布料操作,报告在实机上以毫秒级规划并保持安全裕度。

BibTeX
@misc{li2026robustness,
  title = {{Robustness without Wrinkles: Parallel Simulation and Robust MPC for Certified Deformable Manipulation}},
  author = {Wei-Chen Li and Jeffrey Fang and Sasanka Polisetti and Yuexi Song and Glen Chou},
  year = {2026},
  eprint = {2606.14188},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2606.14188},
}
Paper论文 2026 CoRL 2026 Spotlight new新 2026-11-04

Enabling Robust Cloth Manipulation via Inference-Time Simulator-in-the-Loop Refinement

Refines cloth actions online from one RGB image: a real-to-sim module estimates the cloth state, then simulator rollouts with prior-guided MPPI correct the policy's trajectory.仅凭单张 RGB 在线修正布料动作:先由 real-to-sim 模块估计布料状态,再用仿真器并行推演和先验引导的 MPPI 修正策略轨迹。

BibTeX
@misc{liu2026enabling,
  title = {{Enabling Robust Cloth Manipulation via Inference-Time Simulator-in-the-Loop Refinement}},
  author = {Xin Liu and Yulin Li and Ziming Li and Pengyu Jing and Zhenhao Huang and Bingyang Zhou and Ziqiu Zeng and Siyuan Luo and Chenkun Qi and Fan Shi},
  year = {2026},
  eprint = {2606.24552},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2606.24552},
}
Paper论文 2026 · BrainCo new新 2026-11-09

RevoSim: Scalable Multimodal Tactile Simulation for Dexterous Manipulation

Tactile simulator for the BrainCo Revo3 hand modelling 285 piezoresistive taxels and five visuotactile fingertips (pressure, depth, RGB, marker motion); up to 4,096 parallel envs on one RTX 5090.为 BrainCo Revo3 灵巧手构建的触觉仿真器,同时模拟 285 个压阻触点和五个视触觉指尖(压力、深度、RGB、标记点位移);单张 RTX 5090 最多 4096 个并行环境。

BibTeX
@misc{zhang2026revosim,
  title = {{RevoSim: Scalable Multimodal Tactile Simulation for Dexterous Manipulation}},
  author = {Ke Zhang and Lixin Xu and Ziyi Wang and Xiyue Dong and Jie Tan and Lianghu Shao and Xianpeng Wang and Chuanyu Li and Renjing Xu},
  year = {2026},
  eprint = {2611.08939},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.08939},
}
Paper论文 2026 new新 2026-10-27

Zero-HLM: Generalizable Humanoid Loco-Manipulation without Real Robot Data

Real-to-sim-to-real: smartphone scans become physics-ready sim scenes, whole-body motions are corrected by rollouts, giving 4,800 demos; a sim-only GR00T N1.7 on Unitree G1 reports 66.7% vs. 46.7% trained on real data.真实到仿真再到真实:用手机拍摄重建可物理仿真的场景,并根据仿真回放修正全身动作,生成 4800 条示教;仅用仿真数据训练的 GR00T N1.7 在宇树 G1 上报告平均成功率 66.7%,真实数据训练为 46.7%。

BibTeX
@misc{yang2026zero,
  title = {{Zero-HLM: Generalizable Humanoid Loco-Manipulation without Real Robot Data}},
  author = {Dianyi Yang and Mengya Liu and Zhumei Wang and Yu Liu and Xiaochen Zhang and Yixuan Li and Le Ma and Yuhang Yang and Weiqi Huang and Wei Liang and Baoxiong Jia and Siyuan Huang},
  year = {2026},
  eprint = {2610.35075},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.35075},
}
Paper论文 2026 · Amazon FAR CoRL 2026 new新 2026-11-06

Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation

PRISM turns a few real videos into hundreds of counterfactual human-object clips via video generation, rebuilds them in sim, and trains one humanoid carrying policy that handles unseen objects with no real fine-tuning.PRISM 用视频生成把少量真实视频扩增为数百段反事实人-物交互视频,在仿真中重建并训练单一人形搬运策略,无需真机微调即可泛化到未见物体。

BibTeX
@misc{wang2026counterfactual,
  title = {{Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation}},
  author = {Zihan Wang and Zhen Wu and Pieter Abbeel and Rocky Duan and Jitendra Malik and Carmelo Sferrazza and C. Karen Liu and Guanya Shi and Angjoo Kanazawa},
  year = {2026},
  eprint = {2609.38172},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2609.38172},
}
Paper论文 2026 new新 2026-11-04

PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations

An autoregressive multiview world model running at 10.1 FPS that adapts to held-out robots in 100 to 200 gradient steps; its authors release weights and code and note that fine local calibration still trails.自回归多视角世界模型,运行 10.1 FPS,100 至 200 步梯度即可适配未见平台;作者开放权重和代码,并说明细粒度局部标定仍落后于同类。

BibTeX
@misc{davies2026primesim,
  title = {{PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations}},
  author = {Travis Davies and Wentao Ma and Lihao Guo and Tengfei Ma and Xiaowen Chang and Jiafeng Xu and Shilong Wang and Yiqi Deng and Shaowen He and Xiaoqi Li and Qian Zhu and Ran Cheng and Hao Dong},
  year = {2026},
  eprint = {2611.04870},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.04870},
}
Paper论文 2026 · AgiBot new新 2026-11-04

GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-loop Video World Simulators for Robotic Manipulation

A closed-loop video simulator retrained on thousands of hours of real robot data, with a state expert, a world judge that scores rollouts, and 25-frame rollouts in 2.3 seconds on one H100.闭环视频世界模拟器,用数千小时真机数据重新训练,加入状态专家和为推演打分的世界评判器,在单张 H100 上 2.3 秒生成 25 帧推演。

BibTeX
@misc{qiu2026ge,
  title = {{GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-loop Video World Simulators for Robotic Manipulation}},
  author = {Boxiang Qiu and Liliang Chen and Yue Liao and Nan Wang and Lintao Wang and Jiayi Luo and Wenzhi Zhao and Shengcong Chen and Di Chen and Ye Li and Chen Gao and Shuicheng Yan and Si Liu and Maoqing Yao and Guanghui Ren},
  year = {2026},
  eprint = {2605.27491},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2605.27491},
}
Paper论文 2026 CoRL 2026 new新 2026-11-05

OdorSpaces: Visual-Olfactory Embodied Navigation in 3D Environments

Adds simulated odour transport to Habitat-Sim using Fire Dynamics Simulator, giving a smell-and-vision navigation benchmark for finding invisible gas leaks and early-stage fires, with a multimodal RL baseline.用 Fire Dynamics Simulator 为 Habitat-Sim 加入气味传输仿真,构成视觉加嗅觉的导航基准,任务是定位不可见的气体泄漏和早期火源,并提供多模态强化学习基线。

BibTeX
@misc{lee2026odorspaces,
  title = {{OdorSpaces: Visual-Olfactory Embodied Navigation in 3D Environments}},
  author = {Changyeon Lee and Kelin Yu and Zheng Wei and Shuna Ni and Ruohan Gao},
  year = {2026},
  eprint = {2611.05738},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.05738},
}
Paper论文 2026 CoRL 2026 new新 2026-11-06

CostNav: A Navigation Benchmark for Real-World Economic-Cost Evaluation of Physical AI Agents

Scores delivery-robot navigation by money: cost, revenue and break-even, using Isaac Sim plus public filings and injury data. Reports that none of seven baselines is economically viable yet.以经济账评估配送机器人导航:在 Isaac Sim 中结合公开财报与伤害数据计算成本、收入与盈亏平衡。报告七种基线方法目前都无法盈利。

BibTeX
@misc{seong2025costnav,
  title = {{CostNav: A Navigation Benchmark for Real-World Economic-Cost Evaluation of Physical AI Agents}},
  author = {Haebin Seong and Sungmin Kim and Yongjun Cho and Myunchul Joe and Geunwoo Kim and Yubeen Park and Sunhoo Kim and Samwoo Seong and Yoonshik Kim and Suhwan Choi and Jaeyoon Jung and Jiyong Youn and Jinmyung Kwak and Sunghee Ahn and Jaemin Lee and Younggil Do and Seungyeop Yi and Woojin Cheong and Minhyeok Oh and Minchan Kim and Seongjae Kang and Youngjae Yu and Yunsung Lee},
  year = {2025},
  eprint = {2511.20216},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2511.20216},
}
Paper论文 2026 CoRL 2026 new新 2026-11-06

A Balanced Data Diet: Addressing the Exploration Bottleneck in Mega-Scale RL for Robot Control

Success Guided Sampling focuses massively parallel RL on task configurations at the edge of the policy's ability. With up to a million envs it solves quadruped terrain and assembly tasks; assembly transfers zero-shot.成功引导采样把大规模并行强化学习集中在策略能力边界附近的任务配置上。用最多约一百万个并行环境解决四足多地形与装配任务,装配策略零样本迁移到真机。

BibTeX
@misc{zhang2026balanced,
  title = {{A Balanced Data Diet: Addressing the Exploration Bottleneck in Mega-Scale RL for Robot Control}},
  author = {Octi Zhang and Mateo Guaman Castro and Patrick Yin and Ignacio Dagnino and Abhishek Gupta and Rosario Scalise and Byron Boots},
  year = {2026},
  eprint = {2610.12465},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.12465},
}
Paper论文 2026 · Georgia Tech CoRL 2026 new新 2026-10-19

Active Generative Simulation: Meta-Learning What to Simulate for Sim-and-Real Policy Co-Training

MetaGenSim learns which simulated data to generate, using meta-gradients from real-world performance, instead of sampling the simulator uniformly.MetaGenSim 利用来自真实世界表现的元梯度,学习应该生成哪些仿真数据,而不是对仿真器做均匀采样。

BibTeX
@misc{ma2026active,
  title = {{Active Generative Simulation: Meta-Learning What to Simulate for Sim-and-Real Policy Co-Training}},
  author = {Liqian Ma and Vaibhav Saxena and Utkarsh Aashu Mishra and Shuo Cheng and Yongxin Chen and Danfei Xu},
  year = {2026},
  eprint = {2610.19479},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.19479},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realsim-and-realco-trainingmeta-learning
Paper论文 2026 CoRL 2026 new新 2026-10-22

HyperDrone: Simulation-to-Reality Transfer at Millions of Frames per Second

GPU batch-rendering quadrotor simulator; reports 20×+ the speed of existing batch quadrotor sims, with a new ray tracer rendering RGB, depth, segmentation, normals and optical flow (CoRL 2026).以 GPU 批量渲染为核心的四旋翼仿真器;报告比现有批量四旋翼仿真器快 20 倍以上,新的光线追踪引擎(支持 OptiX、Vulkan、Metal、WebGPU)可渲染 RGB、深度、分割、法向和光流(CoRL 2026)。

BibTeX
@misc{eschmann2026hyperdrone,
  title = {{HyperDrone: Simulation-to-Reality Transfer at Millions of Frames per Second}},
  author = {Jonas Eschmann and Giuseppe Loianno},
  year = {2026},
  eprint = {2610.28950},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.28950},
}
Sim-to-Real & Simulators仿真与 Sim-to-RealDrone / aerial无人机aerialquadrotorsimulatorgpurenderingsim-to-real
Paper论文 2026 new新 2026-10-26

SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning

Generates sim-ready rooms by sampling furniture layouts with diffusion priors, then compiling them into collision-free 3D scenes; nav policies trained there beat ones trained on real scans on held-out real scans.先用扩散先验在功能分区内采样家具布局,再“编译”为无碰撞、可直接仿真的 3D 场景;论文报告在其场景中训练的物体导航策略,在留出的真实扫描场景上优于用等量真实扫描训练的策略。

BibTeX
@misc{liu2026scenebloom,
  title = {{SceneBloom: Agentic Indoor Environment Generation with Realistic and Diverse Layouts for Embodied Learning}},
  author = {Yuhan Liu and Lianhui Qin and Shenji Wan},
  year = {2026},
  eprint = {2610.32978},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2610.32978},
}
Paper论文 2026 new新 2026-10-26

MARE: An Open-Source Lunar Rover Simulator with Shadow Ground Truth for Perception and Autonomy

Unreal Engine 5 + ROS 2 lunar rover simulator: generated cratered terrain, two rovers with stereo, lidar, event and SPAD cameras, pixel-accurate shadow ground truth for low-sun polar lighting, and a GNC stack.基于 Unreal Engine 5 与 ROS 2 的开源月球车仿真:可生成带陨石坑的地形,两台月球车配备双目、激光雷达、事件相机与 SPAD 相机,提供极区低太阳角下像素级的阴影真值,并附 GNC 导航控制栈。

BibTeX
@misc{castillaarquillo2026mare,
  title = {{MARE: An Open-Source Lunar Rover Simulator with Shadow Ground Truth for Perception and Autonomy}},
  author = {Raúl Castilla-Arquillo and Miguel Olivares-Mendez},
  year = {2026},
  eprint = {2610.28465},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.28465},
}
Paper论文 2026 new新 2026-11-01

DexSuite: An All-in-One Framework for Dexterous Manipulation Across Arms, Hands, and Tasks

Open dexterous-manipulation framework on Genesis: 30 tasks, 10 arms × 12 end effectors (100+ single-arm robots), teleoperation, simulated touch, a 16-pair benchmark and 4,700 demo episodes.基于 Genesis 仿真器的开源灵巧操作一体化框架:30 个任务,10 种机械臂与 12 种末端(从平行夹爪到灵巧手)组合出 100 多种单臂机器人和大量双臂组合;自带统一环境 API、遥操作、仿真触觉,定义 16 组任务-本体基准,并发布 4,700 条成功示范。

BibTeX
@misc{houssaini2026dexsuite,
  title = {{DexSuite: An All-in-One Framework for Dexterous Manipulation Across Arms, Hands, and Tasks}},
  author = {Anas Houssaini and Hugo He and Junming Shi and Amin Abyaneh and Ricardo Chahine and Shuo Wen and Mohamad H. Danesh and Charles-Étienne Fréchette and Mariana Sosa Guzman and Mathias Desrochers and Rayan Houssaini and Adam Landa and Theophile Soulie and Charlotte Morissette and Annie Tims and Martino Russi and Jonathan Lussier and Gregory Dudek and Doina Precup and Julen Urain and Hsiu-Chin Lin and David Meger},
  year = {2026},
  eprint = {2610.37799},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.37799},
}
Sim-to-Real & Simulators仿真与 Sim-to-RealManipulation & Dexterous Hands操作与灵巧手Datasets & Benchmarks数据集与基准Robot arm机械臂Dexterous hand灵巧手dexterous-handsgenesisbenchmarkteleoperationtactile-simcross-embodimentsim
Paper论文 2026 new新 2026-11-01

Gym-Anything for Robotics: Scaling physical simulations with digital agents

Coding agents build robotics simulations, checked by an adversarial create-and-audit loop; result RoboWorld: 25 sims chosen by U.S. GDP share, 200 RL envs. Best frontier models average just 0.06 reward on test tasks.把“写仿真”当作编码智能体任务:智能体生成机器人仿真与任务,再由对抗式的创建-审核循环把关;据此构建 RoboWorld(按美国 GDP 构成挑选的 25 个仿真、200 个强化学习环境),最强前沿模型在测试任务上平均奖励仅 0.06。

BibTeX
@misc{aggarwal2026gym,
  title = {{Gym-Anything for Robotics: Scaling physical simulations with digital agents}},
  author = {Pranjal Aggarwal and Sean Welleck},
  year = {2026},
  eprint = {2610.40565},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.40565},
}
Paper论文 2026 · Ai2 CoRL 2026 Oral new新 2026-11-02

MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation

CoRL 2026 Oral. Argues simulation can be enough: large, diverse synthetic data gives zero-shot real transfer for static and mobile manipulation. MolmoBot-Engine is an open procedural data pipeline.CoRL 2026 Oral。挑战“仅靠仿真不够”的观点:足够大规模、多样的合成数据即可零样本迁移到真实静态与移动操作。MolmoBot-Engine 是开源的程序化数据管线。

BibTeX
@misc{deshpande2026molmob,
  title = {{MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation}},
  author = {Abhay Deshpande and Maya Guru and Rose Hendrix and Snehal Jauhri and Ainaz Eftekhar and Rohun Tripathi and Max Argus and Jordi Salvador and Haoquan Fang and Matthew Wallingford and Wilbert Pumacay and Yejin Kim and Quinn Pfeifer and Ying-Chun Lee and Piper Wolters and Omar Rayyan and Mingtong Zhang and Jiafei Duan and Karen Farley and Winson Han and Eli Vanderbilt and Dieter Fox and Ali Farhadi and Georgia Chalvatzaki and Dhruv Shah and Ranjay Krishna},
  year = {2026},
  eprint = {2603.16861},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2603.16861},
}
Sim-to-Real & Simulators仿真与 Sim-to-RealMobile robot移动机器人sim-to-realzero-shotprocedural-datamobile-manipulation
Paper论文 2026 CoRL 2026 Spotlight new新 2026-11-02

Kamino: GPU-based Simulation of Rigid Multi-Body Physics with Kinematic Loops

CoRL 2026 Spotlight. GPU physics solver in Python on NVIDIA Warp, integrated into Newton, for parallel simulation of robots with true kinematic loops rather than tree approximations.CoRL 2026 Spotlight。基于 NVIDIA Warp 的 Python GPU 物理求解器,集成于 Newton,可并行仿真含真实运动学闭环的机器人,而非树形近似。

BibTeX
@misc{tsounis2026kamino,
  title = {{Kamino: GPU-based Simulation of Rigid Multi-Body Physics with Kinematic Loops}},
  author = {Vassilios Tsounis and Guirec Maloisel and Christian Schumacher and Ruben Grandia and Agon Serifi and David Müller and Chris Amevor and Tobias Widmer and Moritz Bächer},
  year = {2026},
  eprint = {2603.16536},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2603.16536},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realgpu-simulationkinematic-loopsnewton
Paper论文 2026 new新 2026-11-03

AuRA: From Atoms to Bits through Autonomous Robot Interaction

Automates the robot interaction and data preparation behind physics-informed digital twins; reports 88.5% less active human labor per asset across 13 deformable objects.自动完成物理数字孪生所需的机器人交互与数据准备;在 13 种柔性物体上报告每个资产的人工投入减少 88.5%。

BibTeX
@misc{yu2026aura,
  title = {{AuRA: From Atoms to Bits through Autonomous Robot Interaction}},
  author = {Xinchen Yu and Yoonkyo Jung and Haoran Chen and Zikui Cai and Aayush Talreja and Seungjae Lee and Hyunjin Kim and Furong Huang},
  year = {2026},
  eprint = {2610.34452},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.34452},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realdigital-twindeformabledata-collection
Paper论文 2026 new新 2026-11-03

Closing the Dynamics Gap through Self-Directed Robotic Interaction

CUE (CoRL 2026 Late Breaking Results): an agent identifies friction and restitution by choosing interactions where its simulation is least accurate; on billiards it reports 72% lower held-out position error.CUE(CoRL 2026 Late Breaking Results):智能体主动选择仿真最不准的交互来辨识摩擦和恢复系数;在台球任务上报告留出位置误差比最强基线低 72%,并部署到真实球桌。

BibTeX
@misc{zhang2026closing,
  title = {{Closing the Dynamics Gap through Self-Directed Robotic Interaction}},
  author = {Xilun Zhang and Liam Achenbach and Luis Pabon and Matthew Foutter and Marco Pavone},
  year = {2026},
  eprint = {2611.02691},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.02691},
}
Paper论文 2026 CoRL 2026 Spotlight new新 2026-11-04

Learning Physics-Guided Residual Dynamics for Deformable Object Simulation

PGRD simulates deformables with an optimizable spring-mass backbone plus learned residuals, reporting better accuracy than either alone; used for MPC and action-conditioned video prediction.PGRD 以可优化的弹簧质点模型为骨架,加上学习得到的残差来仿真可变形物体,报告精度优于单用任一方法;可用于 MPC 和动作条件视频预测。

BibTeX
@misc{patel2026learning,
  title = {{Learning Physics-Guided Residual Dynamics for Deformable Object Simulation}},
  author = {Shivansh Patel and Kaifeng Zhang and Sanjay Pokkali and Svetlana Lazebnik and Yunzhu Li},
  year = {2026},
  eprint = {2607.13451},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2607.13451},
}
Paper论文 2026 new新 2026-11-05

CoDA: Co-Evolution of Data Engines and Action Policies

Turns diagnosed policy failures into new simulated scenes and shaped training signals, so generator and policy improve together; on LIBERO-Pro, reports success rising from 25% to 84% under position perturbations.把诊断出的策略失败转成新的仿真场景和塑形训练信号,让生成器与策略共同进化;在 LIBERO-Pro 上报告位置扰动下成功率从 25% 升至 84%。

BibTeX
@misc{yu2026coda,
  title = {{CoDA: Co-Evolution of Data Engines and Action Policies}},
  author = {Tianjiao Yu and Zhilin Ou and Yifan Shen and Xinzhuo Li and Yuanzhe Liu and Onkar Kishor Susladkar and Fan Wang and Ismini Lourentzou},
  year = {2026},
  eprint = {2610.22362},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.22362},
}
Paper论文 2026 CoRL 2026 new新 2026-11-06

Scaling Sim-to-Real VLA Reinforcement Learning with Generative 3D Worlds

Uses 3D world generative models to build 100 diverse interactive scenes for RL fine-tuning of a VLA. Reports sim success from 9.7% to 79.8% and real-world success from 21.7% to 75%.用 3D 世界生成模型构建 100 个多样的可交互场景,对 VLA 做强化学习微调。报告仿真成功率从 9.7% 提升到 79.8%,真机从 21.7% 提升到 75%。

BibTeX
@misc{choi2026scaling,
  title = {{Scaling Sim-to-Real VLA Reinforcement Learning with Generative 3D Worlds}},
  author = {Andrew Choi and Xinjie Wang and Zhizhong Su and Wei Xu},
  year = {2026},
  eprint = {2603.18532},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2603.18532},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realgenerative-3drl-finetuningvlasim-to-realreal
Paper论文 2026 CoRL 2026 new新 2026-11-06

Worlds in One Demo: A Synthetic Data Engine for Learning Open-World Mobile Manipulation

Synthetic data engine that turns one real mobile-manipulation demo into many: Gaussian-splat scenes, rearranged contact segments chained by whole-body planning, and generated worlds from photos. Also cross-embodiment.合成数据引擎:把一条真实移动操作演示扩展成大量数据——高斯泼溅重建场景、重排接触片段并用全身运动规划串联、再在由照片生成的 3D 世界中合成。也支持跨本体。

BibTeX
@misc{guo2026worlds,
  title = {{Worlds in One Demo: A Synthetic Data Engine for Learning Open-World Mobile Manipulation}},
  author = {Lingxiao Guo and Huanyu Li and Guanya Shi},
  year = {2026},
  eprint = {2607.13154},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2607.13154},
}
Sim-to-Real & Simulators仿真与 Sim-to-RealMobile robot移动机器人data-generationgaussian-splattingmobile-manipulationone-demoreal
Paper论文 2026 CoRL 2026 new新 2026-11-06

SILO: Simulation-in-the-Loop Sim-to-Real Transfer for Multi-Stage Cable Routing

Sim-to-real RL for multi-stage cable routing: GPU-parallel cable simulation, localized policies and a simulation-in-the-loop executor. Reports higher success and 2x shorter cycle times than prior learning methods.多阶段线缆布线的仿真到真机强化学习:GPU 并行线缆仿真、局部化策略,加上执行时“仿真在环”的部署框架。报告成功率更高、节拍时间缩短一半。

BibTeX
@misc{tao2026silo,
  title = {{SILO: Simulation-in-the-Loop Sim-to-Real Transfer for Multi-Stage Cable Routing}},
  author = {Stone Tao and Jie Xu and Hesam Rabeti and Yashraj Narang and Yijie Guo and Iretiayo Akinola},
  year = {2026},
  eprint = {2607.04616},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2607.04616},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realdeformablecable-routingsim-to-realgpu-simulationreal
Paper论文 2026 CoRL 2026 new新 2026-11-06

Sim-to-Real Transfer for Muscle-Actuated Robots via Generalized Actuator Networks

Learns a neural actuator model from joint trajectories alone, combined with rigid-body sim, to transfer RL policies to a pneumatic-muscle arm. Claims the first sim-to-real transfer for a 4-DoF muscle-actuated arm.仅用关节位置轨迹学习神经执行器模型,结合刚体仿真,把强化学习策略迁移到气动人工肌肉机械臂上。声称首次实现 4 自由度肌肉驱动机械臂的仿真到真机迁移。

BibTeX
@misc{schneider2026sim,
  title = {{Sim-to-Real Transfer for Muscle-Actuated Robots via Generalized Actuator Networks}},
  author = {Jan Schneider and Mridul Mahajan and Le Chen and Simon Guist and Bernhard Schölkopf and Ingmar Posner and Dieter Büchler},
  year = {2026},
  eprint = {2604.09487},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2604.09487},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realsim-to-realactuator-networkpneumatic-musclestable-tennisreal
Paper论文 2026 CoRL 2026 new新 2026-11-06

RoboSnap: One-Shot Real-to-Sim Scene Generation for Generalizable Robot Learning and Evaluation

Turns one RGB image into a sim-ready scene: collision-aware foreground assets plus a 3DGS background. Supports synthetic data and sim-real-correlated evaluation; releases DROID-Sim from 564 DROID scenes.把单张 RGB 图像变成可用于仿真的场景:前景为碰撞可靠的资产,背景用 3D 高斯泼溅保持外观。可用于合成训练数据和与真机相关的策略评测;发布由 564 个 DROID 场景构建的 DROID-Sim。

BibTeX
@misc{zhang2026robosnap,
  title = {{RoboSnap: One-Shot Real-to-Sim Scene Generation for Generalizable Robot Learning and Evaluation}},
  author = {Shujie Zhang and Jingkun Yi and Weipeng Zhong and Zirui Zhou and Yangkun Zhu and Hanqing Wang and Xudong Xu and Weinan Zhang and Chunhua Shen},
  year = {2026},
  eprint = {2607.06699},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2607.06699},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realreal-to-simgaussian-splattingscene-generationpolicy-evaluationdroid
Paper论文 2026 CoRL 2026 new新 2026-11-06

ComSim: Building Scalable Real-World Robot Data Generation via Compositional Simulation

Compositional simulation: classical sim produces accurate action-video pairs and a neural simulator restyles them as real-looking video, in a real-sim-real loop seeded by a little real data.组合式仿真:经典仿真生成准确的动作-视频对,再由神经模拟器转换成接近真实的画面,形成以少量真机数据为起点的“真-仿-真”数据扩增闭环。

BibTeX
@misc{qin2026comsim,
  title = {{ComSim: Building Scalable Real-World Robot Data Generation via Compositional Simulation}},
  author = {Yiran Qin and Jiahua Ma and Li Kang and Wenzhan Li and Yihang Jiao and Xin Wen and Xiufeng Song and Heng Zhou and Jiwen Yu and Zhenfei Yin and Xihui Liu and Philip Torr and Yilun Du and Ruimao Zhang},
  year = {2026},
  eprint = {2604.11386},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2604.11386},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realneural-simulationdata-generationsim-to-realvideoreal
Paper论文 2026 CoRL 2026 new新 2026-11-06

UniLab: A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms

CPU-parallel simulation with GPU learning, joined by one runtime for data movement and sync. Reports 3–10x end-to-end training speedups on the same hardware and runs on macOS, ROCm and Intel XPU.CPU 并行仿真 + GPU 策略学习的异构训练架构,用统一运行时处理数据搬运与同步。报告同等硬件下端到端训练效率提升 3–10 倍,并支持 macOS、ROCm 与 Intel XPU。

BibTeX
@misc{jia2026unilab,
  title = {{UniLab: A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms}},
  author = {Yufei Jia and Zhanxiang Cao and Mingrui Yu and Heng Zhang and Shenyu Chen and Dixuan Jiang and Meng Li and Xiaofan Li and Yiyang Liu and Junzhe Wu and Zheng Li and XiLin Fang and Ting-Yu Tsui and Shengcheng Fu and Haoyang Li and Anqi Wang and Zifan Wang and Dongjie Zhu and Chenyu Cao and Zhenbiao Huang and Ziang Zheng and Jie Lu and Xin Ma and Zhengyang Wei and Xiang Zhao and Tianyue Zhan and Ye He and Yuxiang Chen and Yizhou Jiang and Yue Li and Haizhou Ge and Yuhang Dong and Fan Jia and Ziheng Zhang and Meng Zhang and Xiwa Deng and Zhixing Chen and Hanyang Shao and Chenxin Dong and Yixuan Li and Yizhi Chen and Bokui Chen and Kaifeng Zhang and Hanqing Cui and Yusen Qin and Ruqi Huang and Lei Han and Tiancai Wang and Xiang Li and Yue Gao and others},
  year = {2026},
  eprint = {2605.30313},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2605.30313},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realrl-infrastructurecpu-simulationtraining-efficiencymujococross-platform
Paper论文 2026 CoRL 2026 new新 2026-11-06

SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation

Builds sim-ready digital twins from a video and edits them into 'digital cousins'. Sim scores predict real results (mean Pearson 0.911); task cousins add 40% real success for sim-trained policies.从一段视频自动构建可仿真的数字孪生,并编辑出保持可供性的“数字表亲”场景。仿真评测与真机结果高度相关(平均 Pearson 0.911);任务表亲让仿真训练策略的真机成功率提升 40%。

BibTeX
@misc{ranawaka2026simfoundry,
  title = {{SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation}},
  author = {Nadun Ranawaka and Josiah Wong and Wei-Lin Pai and Wei-Teng Chu and Tianyuan Dai and Masoud Moghani and Hang Yin and Yunfan Jiang and Wesley Durbano and Brandon Huynh and Yu Fang and Danfei Xu and Ruohan Zhang and Li Fei-Fei and Linxi Fan and Bowen Wen and Ajay Mandlekar and Yuke Zhu},
  year = {2026},
  eprint = {2606.28276},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2606.28276},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realreal-to-simdigital-twinsscene-generationpolicy-evaluationnvidia
Paper论文 2026 CoRL 2026 new新 2026-11-06

Do Rigid-Body Simulators Dream of Soft Robots? Learning Contact-Rich Manipulation for Tendon-Driven Continuum Robots

Puts tendon-driven continuum robots natively into MuJoCo with a continuum-mechanics-based discretization, validated against Cosserat rods and hardware; sim-trained imitation policies transfer zero-shot to a real robot.以连续介质力学推导的离散化方法,把肌腱驱动连续体机器人原生放进 MuJoCo,并对照 Cosserat 杆模型与真机验证;仿真中训练的模仿策略可零样本迁移到真机富接触任务。

BibTeX
@misc{shentu2026do,
  title = {{Do Rigid-Body Simulators Dream of Soft Robots? Learning Contact-Rich Manipulation for Tendon-Driven Continuum Robots}},
  author = {Chengnan Shentu and Nicholas Baldassini and Tongjia Zheng and Priyanka Rao and Jessica Burgner-Kahrs},
  year = {2026},
  eprint = {2606.22397},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2606.22397},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realsoft-robotscontinuum-robotsmujocosim-to-realreal
Paper论文 2026 CoRL 2026 new新 2026-11-06

AM-Bench: A Modular Simulation Suite and Benchmark for Aerial Manipulation Policy Learning

Benchmark for multirotor aerial manipulation: under-, fully and over-actuated platforms, 12 tasks, configurable wind and saturation, standard low-level controllers and learning baselines for system-level comparison.多旋翼空中操作基准:包含欠驱动、全驱动与过驱动平台,12 个任务,可配置气动扰动与执行器饱和,并提供标准底层控制器和策略学习基线,便于系统级比较。

BibTeX
@misc{wang2026am,
  title = {{AM-Bench: A Modular Simulation Suite and Benchmark for Aerial Manipulation Policy Learning}},
  author = {Yutong Wang and Dongjae Lee and Xiaofeng Guo and Yuanzhu Zhan and Yufei Jiang and Bavin Saravanan and Muqing Cao and Jia Xie and Chenyang Mao and Sebastian Scherer and Junyi Geng and Guanya Shi},
  year = {2026},
  eprint = {2609.00641},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2609.00641},
}
Sim-to-Real & Simulators仿真与 Sim-to-RealDrone / aerial无人机aerial-manipulationbenchmarkdronesim
Paper论文 2026 CoRL 2026 new新 2026-11-06

SIMPLE: Simulation-Based Policy Learning and Evaluation for Humanoid Loco-manipulation

Humanoid loco-manipulation testbed pairing MuJoCo physics with Isaac Sim rendering: 16 whole-body tasks, 50 scenes, 1,000+ objects, motion-planning and VR data pipelines; benchmarks imitation, VLA and WAM policies.人形移动操作仿真平台,结合 MuJoCo 物理与 Isaac Sim 渲染:16 个全身任务、50 个室内场景、1000 多个物体资产,提供运动规划与 VR 数据管线,并评测模仿、VLA 与世界动作模型策略。

BibTeX
@misc{wei2026simple,
  title = {{SIMPLE: Simulation-Based Policy Learning and Evaluation for Humanoid Loco-manipulation}},
  author = {Songlin Wei and Zhenhao Ni and Jie Liu and Zhenyu Zhao and Junjie Ye and Hongyi Jing and Junkai Xia and Xiawei Liu and Michael Leong and Liang Heng and Di Huang and Yue Wang},
  year = {2026},
  eprint = {2606.08278},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2606.08278},
}
Sim-to-Real & Simulators仿真与 Sim-to-RealHumanoid人形humanoidbenchmarkmujocoisaac-simteleoperation
Paper论文 2026 CoRL 2026 Spotlight new新 2026-11-06

VisionSIM: Beyond Idealized Sensors - A Multi-Modal Simulator for Robot Perception

Simulator that models raw measurement physics for event, SPAD, iToF/dToF, LiDAR and thermal sensors, reproducing failure modes like pileup, phase wrapping and refractory drops; releases an indoor dataset.仿真平台对事件相机、SPAD、iToF/dToF、激光雷达和热成像的原始测量物理过程建模,复现堆积、相位缠绕、不应期丢事件等失效模式;并发布室内数据集。

BibTeX
@misc{jungerman2026visionsim,
  title = {{VisionSIM: Beyond Idealized Sensors - A Multi-Modal Simulator for Robot Perception}},
  author = {Sacha Jungerman and Kaustubh Sadekar and Avery Gump and Sriram Narayanan and Shantanu Gupta and Bhuyashi Deka and Srinivasa Narasimhan and Atul Ingle and Mohit Gupta},
  year = {2026},
  eprint = {2611.08368},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.08368},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realsensor-simulationlidarevent-camerathermaldataset
Paper论文 2026 CoRL 2026 new新 2026-11-06

GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning

Agentic generation of functional object compositions (e.g. parts that must fit): disentangled mesh reconstruction, relative pose refinement under geometric and physical guidance, and a VLM verifier.智能体式生成具备功能关系的物体组合:先生成实例分离的网格,再在几何与物理引导下细化相对位姿,最后由 VLM 验证器挑选最符合描述的候选。

BibTeX
@misc{xu2026gif,
  title = {{GIF: Agentic Generation of Interactive and Functional Object Compositions for Robot Learning}},
  author = {Long Xu and Zhiqi Zhang and Mi Yan and Shengliang Deng and Chong Xia and Mingyu Dong and Jiayi Chen and Jiangran Lyu and Fei Gao and Zhizheng Zhang and He Wang},
  year = {2026},
  eprint = {2609.05927},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2609.05927},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realscene-generationassetsvlm-agentfunctional-objects
Paper论文 2026 · University of Tübingen new新 2026-11-09

Lodos: A Lightweight Simulator Designed for Contact-Rich Interactions with Detailed Meshes

GPU rigid-body simulator on NVIDIA Warp for detailed mesh–mesh contact; reports physics on par with established simulators at about 10x their throughput there. Lodos-v2 (2611.08868) adds exact frictional contact.基于 NVIDIA Warp 的 GPU 刚体仿真器,专攻精细网格间接触;物理精度与主流仿真器相当,该场景下吞吐量约高一个数量级。Lodos-v2(2611.08868)进一步求解精确摩擦接触问题。

BibTeX
@misc{beker2026lodos,
  title = {{Lodos: A Lightweight Simulator Designed for Contact-Rich Interactions with Detailed Meshes}},
  author = {Onur Beker and Andreas René Geist and Georg Martius},
  year = {2026},
  eprint = {2611.08872},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.08872},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realsimulatorgpumesh-collisioncontactwarp
Benchmark基准 2026 new新 2026-10-21

RoboCasa-Shift: Stage-Aware Robustness Evaluation of Vision-Language-Action Policies in Long-Horizon Household Manipulation

VLA robustness benchmark on RoboCasa365: paired clean/perturbed rollouts differing in one shift, plus stage-level diagnostics of where long-horizon failures start; evaluated on GR00T N1.5.基于 RoboCasa365 的 VLA 鲁棒性诊断基准:成对比较只差一个分布偏移因素的干净/扰动执行,并定位长时序任务中失败从哪个阶段开始,而不只看总成功率;在 GR00T N1.5 上评测。

BibTeX
@misc{wang2026robocasa,
  title = {{RoboCasa-Shift: Stage-Aware Robustness Evaluation of Vision-Language-Action Policies in Long-Horizon Household Manipulation}},
  author = {Haocheng Wang and Youquan Liu and Weiyu Guo and Aokai Zhang and Donghang Wu and Hongyu Liu and Sha Zhang and Weidong Yang and Ben Fei},
  year = {2026},
  eprint = {2610.27861},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.27861},
}
Benchmark基准 2026 · Tsinghua University, BUPT, NatureWill, Peking University new新 2026-10-24

HandsOn: A Large-Scale Simulation Benchmark for Generalizable Dexterous Manipulation

Isaac Sim benchmark with 5 arms, 6 dexterous hands, ~200 assets and 18k human demos over 66 tasks; reports the best trained policy (a WAM) at only 29.1% on Core-50, near 0% on precision-fit and deformable tasks.基于 Isaac Sim 的灵巧操作基准:5 种机械臂、6 种灵巧手、约 200 个资产、1.8 万条人类演示、66 个任务;报告最好的训练策略(一种世界动作模型)在 Core-50 上仅 29.1%,精密装配和柔性物体任务接近 0%。

BibTeX
@misc{luo2026handson,
  title = {{HandsOn: A Large-Scale Simulation Benchmark for Generalizable Dexterous Manipulation}},
  author = {Tianwei Luo and Yiming He and Hongjin Wu and Ting Pan and Debin Ren and Haorui Guo and Junlin Yang and Yuxin Zuo and Zhehao Kou and Kaisen Yang and Zhuoqun Lai and Yi Ding and Jiale Yu and Yuchen Zhang and Zijie Qiu and Haozhan Li and Ning Ding},
  year = {2026},
  eprint = {2610.26765},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.26765},
}
Paper论文 2026 new新 2026-10-26

AstroBench: Benchmarking Free-Floating Capture and Space Robotic Manipulation

Benchmark for catching drifting, tumbling objects inside a spacecraft with a fixed-base arm, plus storage and servicing tasks. Reports a frozen generalist policy captured only 2/200 static targets.太空机器人操作基准:用固定基座机械臂抓取舱内漂浮、旋转的物体,另含样本存储与在轨维护任务。报告称所测的冻结通用策略在 200 个静止目标中只抓住 2 个。

BibTeX
@misc{wang2026astrobench,
  title = {{AstroBench: Benchmarking Free-Floating Capture and Space Robotic Manipulation}},
  author = {Zizhe Wang and Jia Deng and Xin Lu and Zehao Jia and Yi Huang and Yao Zhu},
  year = {2026},
  eprint = {2610.31064},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.31064},
}
Paper论文 2026 new新 2026-10-27

Behavior Spatial Benchmark: Evaluating Spatial Understanding for Robotics

BEHAVIOR-Spatial, built on BEHAVIOR-1K: spatial QA, point grounding and robot action tests. A baseline policy drops from 41.6% on held-out layouts to 16.1% when the requested target changes; oracle target cues help most.基于 BEHAVIOR-1K 的 BEHAVIOR-Spatial 基准:包含空间问答、指点定位与机器人动作评测。基线策略在未见布局上成功率 41.6%,但在同一布局中更换目标物体指令时降至 16.1%;提供真值目标提示带来的提升最大。

BibTeX
@misc{chen2026behavior,
  title = {{Behavior Spatial Benchmark: Evaluating Spatial Understanding for Robotics}},
  author = {Sirui Chen and Huang Huang and Qineng Wang and Wenlong Huang and Manling Li and Ruohan Zhang and Li Fei-Fei and Jiajun Wu},
  year = {2026},
  eprint = {2610.34051},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.34051},
}
Paper论文 2026 · HexaFuture new新 2026-10-27

EmbodiedLab: Benchmarking Embodied Agents That Act to Know

Benchmark where a robot must run physics experiments to find an unknown answer: 30 experiments, 5 disciplines, parameters resampled per instance. Reports even the best frontier agent succeeds under half the time.“为求知而行动”的基准:机器人在物理仿真实验室中自行操作仪器、读数,测出每次随机重采样的未知参数。共 30 个实验、5 个学科;报告最强的前沿模型智能体在原生控制下成功率也不到一半,失败多源于与仪器交互。

BibTeX
@misc{gao2026embodiedlab,
  title = {{EmbodiedLab: Benchmarking Embodied Agents That Act to Know}},
  author = {Hongcheng Gao and Zelin Zheng and Alex Zhou and Jay Zhu and Shijia Ge and Yazhe Wang and Xiping Li and Jianshu Zeng and Di Wu and Xuan Shangguan and Yexing Wan and Lingyu He and Yongli Wang and Xiaohan Yu and Zhiqi Jia and Yue Liu and Bryan Hooi and Yinpeng Dong and Wentao Zhang and Sihang Wu and Xiao He},
  year = {2026},
  eprint = {2610.35385},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.35385},
}
Paper论文 2026 new新 2026-10-28

SO-101 Bench: Accessible Spatial Manipulation

Isaac Lab digital-twin benchmark for language-conditioned spatial tasks on the low-cost SO-101 arm (138 objects, 916 episodes); sim ranks policies exactly as the real arm. Best VLAs ~61%, an LLM-agent harness 83.2%.基于 Isaac Lab 数字孪生的低成本 SO-101 机械臂语言条件空间操作基准(138 个物体、916 个评测回合);仿真中的策略排名与真机完全一致。最好的 VLA 约 61%,由 LLM 写代码调用抓取策略的方案达 83.2%。

BibTeX
@misc{hickok2026so,
  title = {{SO-101 Bench: Accessible Spatial Manipulation}},
  author = {Truman Hickok},
  year = {2026},
  eprint = {2610.36420},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2610.36420},
}
Paper论文 2026 new新 2026-11-03

ClothDojo: Learned Data Generation and Benchmarking for Bimanual Garment Flattening and Folding

Sim platform where a fine-tuned VLA generates nearly 8,000 successful garment trajectories, re-rendered for RGB policies. Those beat policies trained on the original human data, but unseen garments stay hard.仿真平台:用微调后的 VLA 生成近 8000 条成功的衣物操作轨迹,并重新渲染供 RGB 策略训练,效果优于直接用人类数据训练,但泛化到未见衣物仍是难题。

BibTeX
@misc{huang2026clothdojo,
  title = {{ClothDojo: Learned Data Generation and Benchmarking for Bimanual Garment Flattening and Folding}},
  author = {Zilong Huang and Zipeng Ye and Caicheng Wang and Yuchen Xie and Jiaxiang Luo},
  year = {2026},
  eprint = {2611.01190},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.01190},
}
Paper论文 2026 · Peking University new新 2026-11-04

PyRUA-DataFarm: LLM Agent as a Cost-Efficient Teleoperator for Real-Ready Robot Data

A coding agent rebuilds a task in simulation from one calibration episode, then a video model renders photographic data; reports 93 vs. 84 of 100 real successes against teleop data, at about $107 per hour of data.编程智能体凭一条标定轨迹在仿真中重建任务,再由视频模型渲染成写实数据;报告真机 100 次成功 93 次,遥操作数据为 84 次,每小时数据约 107 美元。

BibTeX
@misc{zhang2026pyrua,
  title = {{PyRUA-DataFarm: LLM Agent as a Cost-Efficient Teleoperator for Real-Ready Robot Data}},
  author = {Kewei Zhang and Juncheng Ma and Guodong Lv and Duomin Wang and Feixiang Ruan and Ruiyang Si and Chuanrui Zhang and Yuxuan Chen and Hao Chen and Yichen Liu and Yintianrun Zhang and Yufan Deng and Enze Xie and Daquan Zhou},
  year = {2026},
  eprint = {2611.05320},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.05320},
}
Paper论文 2026 CoRL 2026 new新 2026-11-06

FoldNet++: a Large-Scale Synthetic Dataset for Robotic T-Shirt Folding and Unfolding

Synthetic T-shirt folding and unfolding data: 6 robots, 1K shirts, 120K episodes. Policies trained only on it are reported above 90% success on unseen real shirts.合成 T 恤折叠与展开数据:6 种机器人、1000 件 T 恤、12 万条轨迹。报告仅用其训练的策略在未见过的真实 T 恤上成功率超过 90%。

BibTeX
@misc{chen2026foldnet,
  title = {{FoldNet++: a Large-Scale Synthetic Dataset for Robotic T-Shirt Folding and Unfolding}},
  author = {Yuxing Chen and Zhiyuan Wei and Bowen Xiao and Zhizheng Zhang and He Wang},
  year = {2026},
  eprint = {2609.12433},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2609.12433},
}
Paper论文 2025 · Peking University (PKU-EPIC) CoRL 2025

GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data

Pretrains a grasping VLA almost only on SynGrasp-1B, a billion-frame photorealistic sim dataset, co-trained with web data; reports zero-shot sim-to-real open-vocabulary grasping and few-shot adaptation.几乎只用十亿帧级的照片级仿真抓取数据集 SynGrasp-1B(并联合网络语义数据)预训练抓取 VLA;论文报告可零样本从仿真迁移到真实开放词汇抓取,并支持少样本适配。

BibTeX
@misc{deng2025graspvla,
  title = {{GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data}},
  author = {Shengliang Deng and Mi Yan and Songlin Wei and Haixin Ma and Yuxin Yang and Jiayi Chen and Zhiqi Zhang and Taoyu Yang and Xuheng Zhang and Wenhao Zhang and Heming Cui and Zhizheng Zhang and He Wang},
  year = {2025},
  eprint = {2505.03233},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2505.03233},
}
Paper论文 2025 new新 2026-11-04

SLAC: Safe and Efficient Real-Robot Reinforcement Learning via Unsupervised Simulation Pre-Training

Pretrains a task-agnostic latent action space in a low-fidelity simulator so real-world RL on high-DoF mobile manipulators becomes safe and efficient.在低保真仿真器中预训练与任务无关的潜在动作空间,让高自由度移动操作机器人的真实世界强化学习安全高效。

BibTeX
@misc{hu2025slac,
  title = {{SLAC: Safe and Efficient Real-Robot Reinforcement Learning via Unsupervised Simulation Pre-Training}},
  author = {Jiaheng Hu and Peter Stone and Roberto Martín-Martín},
  year = {2025},
  eprint = {2506.04147},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2506.04147},
}
Paper论文 2025 · AgiBot, NUS, Beihang University ICLR 2026

Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation

Genie Envisioner (AgiBot) — a video-diffusion world model (GE-Base) plus a flow-matching action decoder (GE-Act), an action-conditioned neural simulator (GE-Sim) and the EWMBench benchmark in one platform.智元 Genie Envisioner:一个平台集成视频扩散世界模型 GE-Base、流匹配动作解码器 GE-Act、动作条件神经仿真器 GE-Sim,以及世界模型评测基准 EWMBench。

BibTeX
@misc{liao2025genie,
  title = {{Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation}},
  author = {Yue Liao and Pengfei Zhou and Siyuan Huang and Donglin Yang and Shengcong Chen and Yuxin Jiang and Yue Hu and Jingbin Cai and Si Liu and Jianlan Luo and Liliang Chen and Shuicheng Yan and Maoqing Yao and Guanghui Ren},
  year = {2025},
  eprint = {2508.05635},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2508.05635},
}
Paper论文 2025 · Shanghai AI Lab CVPR 2025

GenManip: LLM-driven Simulation for Generalizable Instruction-Following Manipulation

Isaac Sim platform where an LLM builds tasks and layouts from a task-oriented scene graph over ~10K objects; its 200-scenario benchmark finds modular foundation-model systems generalize better than end-to-end policies.基于 Isaac Sim 的平台:LLM 依据任务导向场景图,从约 1 万个物体中生成任务与布局;其 200 个场景的基准发现,结合基础模型的模块化系统比端到端策略泛化更好。

BibTeX
@misc{gao2025genmanip,
  title = {{GenManip: LLM-driven Simulation for Generalizable Instruction-Following Manipulation}},
  author = {Ning Gao and Yilun Chen and Shuai Yang and Xinyi Chen and Yang Tian and Hao Li and Haifeng Huang and Hanqing Wang and Tai Wang and Jiangmiao Pang},
  year = {2025},
  eprint = {2506.10966},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2506.10966},
}
Simulator仿真器 2025 NeurIPS 2025 new新 2026-11-04

Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation

GPU tactile simulation combining IPC and ABD; the authors report running 18 times faster than real time across thousands of parallel environments.结合 IPC 与 ABD 的 GPU 触觉仿真;作者报告在数千并行环境下达到实时速度的 18 倍。

BibTeX
@misc{li2025taccel,
  title = {{Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation}},
  author = {Yuyang Li and Wenxin Du and Chang Yu and Puhao Li and Zihang Zhao and Tengyu Liu and Chenfanfu Jiang and Yixin Zhu and Siyuan Huang},
  year = {2025},
  eprint = {2504.12908},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2504.12908},
}
Paper论文 2025 new新 2026-11-04

GaussGym: An open-source real-to-sim framework for learning locomotion from pixels

Drops 3D Gaussian Splatting into vectorized physics simulators as a renderer, reporting over 100,000 steps per second on consumer GPUs for learning from pixels.把 3D 高斯溅射作为渲染器接入矢量化物理仿真,报告在消费级 GPU 上超过每秒 10 万步,用于从像素学习。

BibTeX
@misc{escontrela2025gaussgym,
  title = {{GaussGym: An open-source real-to-sim framework for learning locomotion from pixels}},
  author = {Alejandro Escontrela and Justin Kerr and Arthur Allshire and Jonas Frey and Rocky Duan and Carmelo Sferrazza and Pieter Abbeel},
  year = {2025},
  eprint = {2510.15352},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2510.15352},
}
Paper论文 2025 CoRL 2026 new新 2026-11-06

Procedural Generation of Articulated Simulation-Ready Assets

Infinigen-Articulated: procedural generators for 18 articulated object categories plus Blender tools and an export pipeline into common robot simulators, with physical properties.Infinigen-Articulated:涵盖 18 类常见铰接物体的程序化生成器,附带 Blender 工具,并可连同物理属性导出到常用机器人仿真器。

BibTeX
@misc{joshi2025procedural,
  title = {{Procedural Generation of Articulated Simulation-Ready Assets}},
  author = {Abhishek Joshi and Beining Han and Jack Nugent and Max Gonzalez Saez-Diez and Yiming Zuo and Jonathan Liu and Hongyu Wen and Stamatis Alexandropoulos and Karhan Kayan and Anna Calveri and Tao Sun and Gaowen Liu and Yi Shao and Alexander Raistrick and Jia Deng},
  year = {2025},
  eprint = {2505.10755},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2505.10755},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realassetsarticulated-objectsproceduralblendersim2real
Paper论文 2024 · Sun Yat-sen University (HCPLab)

Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI

Broad embodied-AI survey — robots, simulators, embodied perception, interaction, agents and sim-to-real — with the role of multimodal and world models; backed by the widely used HCPLab paper list.覆盖面很广的具身智能综述:机器人本体、仿真器、具身感知、交互、具身智能体与 sim-to-real,并讨论多模态大模型与世界模型的作用;配套中山大学 HCPLab 维护的常用论文列表。

BibTeX
@misc{liu2024aligning,
  title = {{Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI}},
  author = {Yang Liu and Weixing Chen and Yongjie Bai and Xiaodan Liang and Guanbin Li and Wen Gao and Liang Lin},
  year = {2024},
  eprint = {2407.06886},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2407.06886},
}
Paper论文 2024 · NVIDIA

TacSL: A Library for Visuotactile Sensor Simulation and Learning

GPU-based simulation of GelSight-style tactile images and contact forces in Isaac Gym, plus learning tools for sim-to-real transfer of visuotactile policies.在 Isaac Gym 中用 GPU 模拟 GelSight 式触觉图像与接触力,并提供用于视触觉策略仿真到真实迁移的学习工具。

BibTeX
@misc{akinola2024tacsl,
  title = {{TacSL: A Library for Visuotactile Sensor Simulation and Learning}},
  author = {Iretiayo Akinola and Jie Xu and Jan Carius and Dieter Fox and Yashraj Narang},
  year = {2024},
  eprint = {2408.06506},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2408.06506},
}
Paper论文 2024 · NVIDIA, UT Austin ICRA 2025

DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning

Extends MimicGen to humanoids with two dexterous hands, turning 60 human demos into 21K simulated ones across bimanual tasks, plus a real-to-sim-to-real pipeline tested on real can sorting.把 MimicGen 扩展到双灵巧手人形机器人,从 60 条人类演示生成 2.1 万条双臂仿真演示,并给出在真实分拣罐子任务上验证的 real-to-sim-to-real 流程。

BibTeX
@misc{jiang2024dexmimicgen,
  title = {{DexMimicGen: Automated Data Generation for Bimanual Dexterous Manipulation via Imitation Learning}},
  author = {Zhenyu Jiang and Yuqi Xie and Kevin Lin and Zhenjia Xu and Weikang Wan and Ajay Mandlekar and Linxi Fan and Yuke Zhu},
  year = {2024},
  eprint = {2410.24185},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2410.24185},
}
Sim-to-Real & Simulators仿真与 Sim-to-RealManipulation & Dexterous Hands操作与灵巧手Datasets & Benchmarks数据集与基准Robot arm机械臂Dexterous hand灵巧手Humanoid人形simhumanoiddexterous-handbimanualdata-generationimitation
Simulator仿真器 2024 ICLR 2024 new新 2026-11-04

DIFFTACTILE: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation

Differentiable tactile simulator with an FEM soft-body elastomer model, built for contact with many material types rather than mostly rigid objects.可微触觉仿真器,用 FEM 软体模型模拟弹性体,面向多种材料的接触,而非主要针对刚体。

BibTeX
@misc{si2024difftactile,
  title = {{DIFFTACTILE: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation}},
  author = {Zilin Si and Gu Zhang and Qingwei Ben and Branden Romero and Zhou Xian and Chao Liu and Chuang Gan},
  year = {2024},
  eprint = {2403.08716},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2403.08716},
}
Simulator仿真器 2024 new新 2026-11-04

TacEx: GelSight Tactile Simulation in Isaac Sim -- Combining Soft-Body and Visuotactile Simulators

Brings GIPC soft-body contact and the Taxim and FOTS tactile simulators into Isaac Sim for GelSight Mini, with Isaac Lab RL environments.把 GIPC 软体接触与 Taxim、FOTS 触觉仿真器接入 Isaac Sim,模拟 GelSight Mini,并提供 Isaac Lab 强化学习环境。

BibTeX
@misc{nguyen2024tacex,
  title = {{TacEx: GelSight Tactile Simulation in Isaac Sim -- Combining Soft-Body and Visuotactile Simulators}},
  author = {Duc Huy Nguyen and Tim Schneider and Guillaume Duret and Alap Kshirsagar and Boris Belousov and Jan Peters},
  year = {2024},
  eprint = {2411.04776},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2411.04776},
}
Benchmark基准 2024 new新 2026-11-04

BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark

Benchmark of 40 home tasks for mobile bimanual robots, from reaching to kitchen cleaning, each with human-collected demonstrations.面向移动双臂机器人的基准,含 40 个家庭任务(从抓取到厨房清洁),均配人类采集的演示。

BibTeX
@misc{chernyadev2024bigym,
  title = {{BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark}},
  author = {Nikita Chernyadev and Nicholas Backshall and Xiao Ma and Yunfan Lu and Younggyo Seo and Stephen James},
  year = {2024},
  eprint = {2407.07788},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2407.07788},
}
Benchmark基准 2024 ICLR 2025 new新 2026-11-04

ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks

GPU-accelerated Home Assistant Benchmark with realistic low-level control; the authors report over 3x the speed of prior magical-grasp versions.GPU 加速的 Home Assistant Benchmark,采用真实低层控制;作者报告速度超过此前“魔法抓取”实现的 3 倍。

BibTeX
@misc{shukla2024maniskill,
  title = {{ManiSkill-HAB: A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks}},
  author = {Arth Shukla and Stone Tao and Hao Su},
  year = {2024},
  eprint = {2412.13211},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2412.13211},
}
Paper论文 2024 ICCV 2025

UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI

Over 100 photorealistic Unreal Engine worlds with playable humans, animals, robots and vehicles for embodied AI research.100 多个基于虚幻引擎的高真实感世界,含可操控的人、动物、机器人和车辆,服务具身智能研究。

BibTeX
@misc{zhong2024unrealzoo,
  title = {{UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI}},
  author = {Fangwei Zhong and Kui Wu and Churan Wang and Hao Chen and Hai Ci and Zhoujun Li and Yizhou Wang},
  year = {2024},
  eprint = {2412.20977},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2412.20977},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realsimulatorunreal-enginephotorealistic
Benchmark基准 2024 · UC Berkeley · Yonsei University RSS 2024

HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation

27 simulated tasks (12 locomotion, 15 whole-body manipulation) on a Unitree H1 with two dexterous hands; reports that DreamerV3, TD-MPC2, SAC and PPO fail most of them, especially long-horizon whole-body ones.27 个仿真任务(12 个运动、15 个全身操作),机器人为带两只灵巧手的 Unitree H1;报告 DreamerV3、TD-MPC2、SAC、PPO 在大多数任务上未达标,长时程全身协调任务尤甚。

BibTeX
@misc{sferrazza2024humanoidbench,
  title = {{HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation}},
  author = {Carmelo Sferrazza and Dun-Ming Huang and Xingyu Lin and Youngwoon Lee and Pieter Abbeel},
  year = {2024},
  eprint = {2403.10506},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2403.10506},
}
Paper论文 2023 · NVIDIA, UT Austin CoRL 2023

MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations

Turns a handful of human demos into thousands by splitting them into object-centric segments and replaying those segments in new scenes; widely reused to scale imitation data.把少量人类演示切分为以物体为中心的片段,并在新场景中变换重放,从而扩增为数千条演示;被广泛用于扩充模仿学习数据。

BibTeX
@misc{mandlekar2023mimicgen,
  title = {{MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations}},
  author = {Ajay Mandlekar and Soroush Nasiriany and Bowen Wen and Iretiayo Akinola and Yashraj Narang and Linxi Fan and Yuke Zhu and Dieter Fox},
  year = {2023},
  eprint = {2310.17596},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2310.17596},
}
Simulator仿真器 2022 · University of Bristol

Tactile Gym 2.0: Sim-to-real Deep Reinforcement Learning for Comparing Low-cost High-Resolution Robot Touch

Open-source tactile RL environments with sim-to-real transfer across three low-cost optical sensors (TacTip, DIGIT, DigiTac), for comparing them on the same tasks.开源触觉强化学习环境,支持三种低成本光学触觉传感器(TacTip、DIGIT、DigiTac)的仿真到真机迁移,便于在相同任务上比较。

BibTeX
@misc{lin2022tactile,
  title = {{Tactile Gym 2.0: Sim-to-real Deep Reinforcement Learning for Comparing Low-cost High-Resolution Robot Touch}},
  author = {Yijiong Lin and John Lloyd and Alex Church and Nathan F. Lepora},
  year = {2022},
  eprint = {2207.10763},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2207.10763},
}
Dataset数据集 2022 · Allen Institute for AI CVPR 2023

Objaverse: A Universe of Annotated 3D Objects

800K+ annotated 3D object models; widely used to populate simulators with diverse objects for grasping, rearrangement and procedural scene generation (Objaverse-XL extends it to 10M+).80 万+ 带标注的 3D 物体模型,常用于为仿真器填充多样物体,用于抓取、重排和程序化场景生成(Objaverse-XL 扩展到 1000 万+)。

BibTeX
@misc{deitke2022objaverse,
  title = {{Objaverse: A Universe of Annotated 3D Objects}},
  author = {Matt Deitke and Dustin Schwenk and Jordi Salvador and Luca Weihs and Oscar Michel and Eli VanderBilt and Ludwig Schmidt and Kiana Ehsani and Aniruddha Kembhavi and Ali Farhadi},
  year = {2022},
  eprint = {2212.08051},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2212.08051},
}
Simulator仿真器 2021 · CMU

Taxim: An Example-based Simulation Model for GelSight Tactile Sensors

Simulates GelSight images from calibration examples (optical lookup + linear elastic deformation) instead of physics-based rendering, so tactile data can be generated quickly.用标定样本(光学查找表 + 线弹性形变)而不是基于物理的渲染来模拟 GelSight 图像,可快速生成触觉数据。

BibTeX
@misc{si2021taxim,
  title = {{Taxim: An Example-based Simulation Model for GelSight Tactile Sensors}},
  author = {Zilin Si and Wenzhen Yuan},
  year = {2021},
  eprint = {2109.04027},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2109.04027},
}
Paper论文 2021 · NVIDIA

Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning

Keeps physics and policy on the GPU end-to-end, enabling thousands of parallel environments on one card.物理仿真与策略全程在 GPU 上运行,单卡即可并行数千个环境。

BibTeX
@misc{makoviychuk2021isaac,
  title = {{Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning}},
  author = {Viktor Makoviychuk and Lukasz Wawrzyniak and Yunrong Guo and Michelle Lu and Kier Storey and Miles Macklin and David Hoeller and Nikita Rudin and Arthur Allshire and Ankur Handa and Gavriel State},
  year = {2021},
  eprint = {2108.10470},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2108.10470},
}
Paper论文 2021 · Meta AI NeurIPS 2021

Habitat 2.0: Training Home Assistants to Rearrange their Habitat

Adds fast rigid-body physics and an interactive apartment dataset (ReplicaCAD) to Habitat, plus a home-rearrangement benchmark for mobile manipulators.为 Habitat 加入快速刚体物理与可交互公寓数据集 ReplicaCAD,并提出面向移动操作机器人的家居物品重排基准。

BibTeX
@misc{szot2021habitat,
  title = {{Habitat 2.0: Training Home Assistants to Rearrange their Habitat}},
  author = {Andrew Szot and Alex Clegg and Eric Undersander and Erik Wijmans and Yili Zhao and John Turner and Noah Maestre and Mustafa Mukadam and Devendra Chaplot and Oleksandr Maksymets and Aaron Gokaslan and Vladimir Vondrus and Sameer Dharur and Franziska Meier and Wojciech Galuba and Angel Chang and Zsolt Kira and Vladlen Koltun and Jitendra Malik and Manolis Savva and Dhruv Batra},
  year = {2021},
  eprint = {2106.14405},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2106.14405},
}
Dataset数据集 2021 · Meta AI, Matterport NeurIPS 2021

Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI

1,000 3D scans of real indoor spaces for Habitat; the main scene set behind ObjectNav and many embodied navigation benchmarks.1000 个真实室内空间的 3D 扫描,供 Habitat 使用;ObjectNav 等众多具身导航基准的主要场景集。

BibTeX
@misc{ramakrishnan2021habitat,
  title = {{Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI}},
  author = {Santhosh K. Ramakrishnan and Aaron Gokaslan and Erik Wijmans and Oleksandr Maksymets and Alex Clegg and John Turner and Eric Undersander and Wojciech Galuba and Andrew Westbury and Angel X. Chang and Manolis Savva and Yili Zhao and Dhruv Batra},
  year = {2021},
  eprint = {2109.08238},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2109.08238},
}
Paper论文 2020 · Meta AI

TACTO: A Fast, Flexible, and Open-source Simulator for High-Resolution Vision-based Tactile Sensors

Renders DIGIT/GelSight-style tactile images in simulation so touch-based policies can be trained at scale.在仿真中渲染 DIGIT/GelSight 式触觉图像,便于大规模训练基于触觉的策略。

BibTeX
@misc{wang2020tacto,
  title = {{TACTO: A Fast, Flexible, and Open-source Simulator for High-Resolution Vision-based Tactile Sensors}},
  author = {Shaoxiong Wang and Mike Lambeta and Po-Wei Chou and Roberto Calandra},
  year = {2020},
  eprint = {2012.08456},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2012.08456},
}
Paper论文 2020 · UC San Diego

SAPIEN: A SimulAted Part-based Interactive ENvironment

A simulator with large-scale articulated objects (PartNet-Mobility) for interaction tasks like opening drawers.包含大规模铰接物体(PartNet-Mobility)的仿真器,适合开抽屉等交互任务。

BibTeX
@misc{xiang2020sapien,
  title = {{SAPIEN: A SimulAted Part-based Interactive ENvironment}},
  author = {Fanbo Xiang and Yuzhe Qin and Kaichun Mo and Yikuan Xia and Hao Zhu and Fangchen Liu and Minghua Liu and Hanxiao Jiang and Yifu Yuan and He Wang and Li Yi and Angel X. Chang and Leonidas J. Guibas and Hao Su},
  year = {2020},
  eprint = {2003.08515},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2003.08515},
}
Paper论文 2020 · Carnegie Mellon University CoRL 2020

SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation

Open-source Gym-style benchmark for manipulating deformable objects such as cloth, rope and liquids; shows that high-dimensional, partially observable states make these tasks hard for standard RL.开源、Gym 接口的可变形物体操作基准(布料、绳子、液体等);实验表明高维且部分可观测的状态让这类任务对常规强化学习方法很困难。

BibTeX
@misc{lin2020softgym,
  title = {{SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation}},
  author = {Xingyu Lin and Yufei Wang and Jake Olkin and David Held},
  year = {2020},
  eprint = {2011.07215},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2011.07215},
}
Paper论文 2017 · OpenAI

Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World

Randomizing textures, lighting and cameras in sim makes vision models work on real images with no real data.在仿真中随机化纹理、光照和相机,使视觉模型无需真实数据即可在真实图像上工作。

BibTeX
@misc{tobin2017domain,
  title = {{Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World}},
  author = {Josh Tobin and Rachel Fong and Alex Ray and Jonas Schneider and Wojciech Zaremba and Pieter Abbeel},
  year = {2017},
  eprint = {1703.06907},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/1703.06907},
}
Paper论文 2017 · OpenAI, UC Berkeley

Sim-to-Real Transfer of Robotic Control with Dynamics Randomization

Randomizing physical parameters during training yields control policies robust enough to run on a real arm.训练中随机化物理参数,得到足以在真实机械臂上运行的鲁棒控制策略。

BibTeX
@misc{peng2017sim,
  title = {{Sim-to-Real Transfer of Robotic Control with Dynamics Randomization}},
  author = {Xue Bin Peng and Marcin Andrychowicz and Wojciech Zaremba and Pieter Abbeel},
  year = {2017},
  eprint = {1710.06537},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/1710.06537},
}
Sim-to-Real & Simulators仿真与 Sim-to-Realsim2realdomain-randomizationrl

Recent arXiv papers近期 arXiv 论文 (auto-tagged自动标注 · Atom feedAtom 订阅)

arXiv cs.RO 2026-11-10

Simulating Vein Compressibility for Ultrasound-Guided Femoral Access: Speed, Accuracy, and Phantom Validation

Amit Manicka, Laurent Coulon, Darwin Ang, Michael Loushin et al.

Abstract摘要

In ultrasound-guided femoral access, probe pressure deforms the tissue and changes the vascular anatomy a robot observes. A simulator must reproduce these mechanics fast enough for robotic interaction, yet the computational effort needed for a clinically meaningful signal like vein collapse before artery is unclear. We test the feasibility of a physics-based simulation in NVIDIA's Isaac Sim for Healthcare, with Stable Neo-Hookean tissue solved by Vertex Block Descent on one GPU. A simulation of a low-fidelity cylindrical benchtop phantom with known geometry and mechanical properties, pressed …

BibTeX
@misc{manicka2026simulating,
  title = {{Simulating Vein Compressibility for Ultrasound-Guided Femoral Access: Speed, Accuracy, and Phantom Validation}},
  author = {Amit Manicka and Laurent Coulon and Darwin Ang and Michael Loushin and Timothy M. Kowalewski},
  year = {2026},
  eprint = {2611.12818},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.12818},
}
arXiv cs.LG 2026-11-10 code NeurIPS 2026

Simulation-aided Reinforcement Learning with Control Variates

Omer Hemo, Ido Sefi, Mirco Mutti, Aviv Tamar et al.

Abstract摘要

Reinforcement Learning (RL) algorithms often rely on data collected from a target environment, which can be expensive and noisy. Although simulators can generate large amounts of additional data, standard simulation mixing approaches, which directly combine simulated and real experience, can degrade performance due to simulator inaccuracies, especially when they bias the solution away from the optimal policy. We propose a conservative simulation-aided learning method based on control variates, where simulated data is used solely to reduce variance in the learning process rather than directly …

BibTeX
@misc{hemo2026simulation,
  title = {{Simulation-aided Reinforcement Learning with Control Variates}},
  author = {Omer Hemo and Ido Sefi and Mirco Mutti and Aviv Tamar and Kfir Y. Levy},
  year = {2026},
  eprint = {2611.12643},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2611.12643},
}
arXiv cs.RO 2026-11-10

From Festival Video to the Stage: A Sim-to-Real Ladder for Long-Horizon Expressive Whole-Body Dance on a Commercial Humanoid

Hesham Shehata

Abstract摘要

We present a pipeline for transferring Awa Odori, a traditional Japanese festival dance, from monocular video to a commercial Unitree G1 EDU humanoid. The pipeline combines human mesh recovery, kinematic retargeting, reinforcement learning for motion tracking in simulation, and onboard deployment via ONNX. Training ran on a single RTX 5070 GPU. An eleven-version deployment ladder evaluated on hardware examines three interventions. We detect and repair silent corruption of deployment artifacts, model state-estimator drift during training, and edit the reference motion to support stable …

BibTeX
@misc{shehata2026from,
  title = {{From Festival Video to the Stage: A Sim-to-Real Ladder for Long-Horizon Expressive Whole-Body Dance on a Commercial Humanoid}},
  author = {Hesham Shehata},
  year = {2026},
  eprint = {2611.11127},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.11127},
}
arXiv cs.RO 2026-11-09

Autonomous Particle Image Velocimetry Using Zero-Shot Sim-to-Real Reinforcement Learning

Chang Rajani, Luke Sebastien Marsden, Stephan Kunz, Claudio Mucignat et al.

Abstract摘要

Particle image velocimetry (PIV) reconstructs a flow field from the motion of tracer particles but the reconstruction quality is bounded by how well the flow structure of interest is resolved in the images. The acquisition position is typically fixed by the operator before the measurement. We cast camera placement as a sequential decision-making problem and train a reinforcement learning agent to control a 6-DoF manipulator equipped with a camera, enabling it to locate, frame and resolve a hydrofoil wake in a water tunnel. The agent commands the camera pose and observes the scene only through …

BibTeX
@misc{rajani2026autonomous,
  title = {{Autonomous Particle Image Velocimetry Using Zero-Shot Sim-to-Real Reinforcement Learning}},
  author = {Chang Rajani and Luke Sebastien Marsden and Stephan Kunz and Claudio Mucignat and Ivan Lunati},
  year = {2026},
  eprint = {2611.09679},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.09679},
}
arXiv cs.LG 2026-11-09

Probably Safe Sim-to-Real Transfer with Lifetime Validity

Rohan Tangri, Jan-Peter Calliess

Abstract摘要

We present Dejavu, a method that makes sim-to-real transfer of reinforcement learning policies in constrained Markov decision processes probably safe over an unbounded sequence of policy updates. An anytime valid test using per-decision importance sampling and a betting confidence sequence certifies each candidate trained in simulation before deployment using only trajectories collected by a safe baseline policy operating in production. Simulation quality does not affect the safety guarantee, only the production sample efficiency of the method. Finally, a summable per-test failure probability …

BibTeX
@misc{tangri2026probably,
  title = {{Probably Safe Sim-to-Real Transfer with Lifetime Validity}},
  author = {Rohan Tangri and Jan-Peter Calliess},
  year = {2026},
  eprint = {2611.09344},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2611.09344},
}
arXiv cs.RO 2026-11-09 code

RevoSim: Scalable Multimodal Tactile Simulation for Dexterous Manipulation

Ke Zhang, Lixin Xu, Ziyi Wang, Xiyue Dong et al.

Abstract摘要

We present RevoSim, a scalable and high-fidelity multimodal tactile simulator for the BrainCo Revo3 hand that jointly models 285 piezoresistive taxels and five visuotactile fingertips. RevoSim efficiently generates synchronized pressure, depth, RGB, and marker-displacement observations; on a single RTX 5090, its depth-conditioned marker-displacement configuration supports up to 4,096 parallel environments. We train in-hand manipulation and grasping policies entirely in simulation, establishing a foundation for future sim-to-real transfer. Project page: …

BibTeX
@misc{zhang2026revosim,
  title = {{RevoSim: Scalable Multimodal Tactile Simulation for Dexterous Manipulation}},
  author = {Ke Zhang and Lixin Xu and Ziyi Wang and Xiyue Dong and Jie Tan and Lianghu Shao and Xianpeng Wang and Chuanyu Li and others},
  year = {2026},
  eprint = {2611.08939},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.08939},
}
arXiv cs.RO 2026-11-09 code

Lodos: A Lightweight Simulator Designed for Contact-Rich Interactions with Detailed Meshes

Onur Beker, Andreas René Geist, Georg Martius

Abstract摘要

In recent years, massively parallelized rigid-body simulation has played a central role in robotics research, enabling rapid progress in areas such as reinforcement learning, stochastic optimal control, and randomized smoothing-based trajectory optimization. Particularly in contact-rich settings, the scalability of such simulations in large part depends on well-optimized representations of collision geometry, often requiring a coarse approximation of the underlying surfaces using primitives such as spheres, capsules, cylinders, and boxes. Whenever the complexity of the surfaces or the …

BibTeX
@misc{beker2026lodos,
  title = {{Lodos: A Lightweight Simulator Designed for Contact-Rich Interactions with Detailed Meshes}},
  author = {Onur Beker and Andreas René Geist and Georg Martius},
  year = {2026},
  eprint = {2611.08872},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.08872},
}
arXiv cs.RO 2026-11-06 CoRL 2026 Spotlight

VisionSIM: Beyond Idealized Sensors - A Multi-Modal Simulator for Robot Perception

Sacha Jungerman, Kaustubh Sadekar, Avery Gump, Sriram Narayanan et al.

Abstract摘要

Robotic perception increasingly relies on heterogeneous sensor suites combining cameras with emerging modalities (event, SPAD, iToF/dToF, and thermal). Yet existing simulators idealize these sensors, hiding critical modality-specific failure modes that limit real-world deployment. We present VisionSIM, a unified, physically grounded simulation platform that elevates sensor realism to a first-class concern by modeling the raw physical measurement process for diverse conventional and emerging modalities. We expose fine-grained control over physical sensor parameters, reproducing failure modes …

BibTeX
@misc{jungerman2026visionsim,
  title = {{VisionSIM: Beyond Idealized Sensors - A Multi-Modal Simulator for Robot Perception}},
  author = {Sacha Jungerman and Kaustubh Sadekar and Avery Gump and Sriram Narayanan and Shantanu Gupta and Bhuyashi Deka and Srinivasa Narasimhan and Atul Ingle and others},
  year = {2026},
  eprint = {2611.08368},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.08368},
}
arXiv cs.RO 2026-11-06

TactileLab: Sim-to-Real Dexterous Robot Manipulation with Efficient Shear-Sensitive Tactile Simulation

Yijiong Lin, Wenhao He, Toby Jack, Max Yang et al.

Abstract摘要

Robotic simulators that represent shear within tactile sensing are becoming increasingly important for contact-rich manipulation. However, simulating contact shear with high-fidelity deformable or soft-body simulation is computationally demanding, limiting scalability to large-scale reinforcement learning. Here we introduce \textit{TactileLab}, a scalable multimodal tactile simulation framework built on IsaacLab, with a particular focus on a new optical-flow-based tactile representation termed \textit{simulated tactile flow}. Instead of relying on soft-body physics to model shear deformation, …

BibTeX
@misc{lin2026tactilelab,
  title = {{TactileLab: Sim-to-Real Dexterous Robot Manipulation with Efficient Shear-Sensitive Tactile Simulation}},
  author = {Yijiong Lin and Wenhao He and Toby Jack and Max Yang and Haoran Li and Nathan F. Lepora},
  year = {2026},
  eprint = {2611.07881},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.07881},
}
arXiv cs.RO 2026-11-06

GraspBench: Execution-Aware Cross-Robot Evaluation of 6-DoF Grasp Generation in MuJoCo

Abdul Basit, Bibek Poudel, Muhammad Shafique

Abstract摘要

Modern 6-DoF grasp generators are often evaluated using grasp scores, dataset-level metrics, or single-robot demonstrations, yet proposal quality alone does not determine whether a grasp is executable by a particular robot. We present GraspBench, a controlled MuJoCo protocol for evaluating complete grasp-generation pipelines after robot-specific inverse-kinematics filtering, motion planning, and fixed approach-close-lift execution. GraspBench evaluates six configured pipelines across four robot embodiments, five diagnostic objects, and a structured tabletop pose grid, yielding 540 scenarios …

BibTeX
@misc{basit2026graspbench,
  title = {{GraspBench: Execution-Aware Cross-Robot Evaluation of 6-DoF Grasp Generation in MuJoCo}},
  author = {Abdul Basit and Bibek Poudel and Muhammad Shafique},
  year = {2026},
  eprint = {2611.07651},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.07651},
}
arXiv cs.RO 2026-11-06

An Empirical Study of Reinforcement Learning for Keypoint Positioning of Deformable Linear Objects

Vinay Rodrigues, Sara Zeynalpour, Gokhan Solak, Sebastian Hjorth et al.

Abstract摘要

Deformable linear object (DLO) manipulation is challenging because high-dimensional configurations, nonlinear contact dynamics, and diverse material and geometric properties produce a broad range of object responses that are both difficult to model and data-intensive to learn. This work studies reinforcement learning for planar manipulation of a one-end-grasped DLO, focusing on training efficiency, observation design, robustness, and zero-shot sim-to-real transfer. We compare three Proximal Policy Optimization training stacks and find that the GPU-parallel MuJoCo Playground stack enables …

BibTeX
@misc{rodrigues2026empirical,
  title = {{An Empirical Study of Reinforcement Learning for Keypoint Positioning of Deformable Linear Objects}},
  author = {Vinay Rodrigues and Sara Zeynalpour and Gokhan Solak and Sebastian Hjorth and Arash Ajoudani},
  year = {2026},
  eprint = {2611.07261},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.07261},
}
arXiv cs.RO 2026-11-06

When Does Test-Time Search Help World Action Models? An Empirical Audit of Candidate Selection and Simulator Integrity

Jun Liu, Dajie Sun, Zhenglun Kong, Zhenjiang Fan et al.

Abstract摘要

World-action models increasingly apply test-time scaling, spending extra inference computation on candidate selection and adaptive allocation to improve control. Such gains are credible only when candidates carry exploitable signal, nominal compute savings become real speedup, and evaluation stays reliable. We audit all three on Cosmos Policy and RoboCasa with a premise-first, pre-registered methodology. On clean data, a learned value selector is 1.66 pp worse than random; a hindsight oracle gains only 1.40 pp, with an episode-level interval spanning zero; and 82% of states show identical …

BibTeX
@misc{liu2026when,
  title = {{When Does Test-Time Search Help World Action Models? An Empirical Audit of Candidate Selection and Simulator Integrity}},
  author = {Jun Liu and Dajie Sun and Zhenglun Kong and Zhenjiang Fan and Peiyan Dong and Fan Yang and Wenbin Zhang and Geng Yuan and others},
  year = {2026},
  eprint = {2610.41970},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.41970},
}
arXiv cs.RO 2026-11-05

TwinBridge: Digital Twin-Driven Policy and Reward Transfer for Real-World Reinforcement Learning in Laboratory Robotics

Shu'ang Sun, Yibo Qiu, Haoliang Ye, Zan Huang et al.

Abstract摘要

Online reinforcement learning offers an effective approach to precise laboratory manipulation, yet costly real-world demonstrations and limited access to dense process rewards hinder its practical application. We present TwinBridge, a digital twin-driven framework that supplies policy initialization and dense visual rewards for real-world online learning. We construct digital twins by combining 3D Gaussian splatting with physics simulation. Here, simulator states provide task events and geometric progress under physical prerequisites and ordering constraints, yielding rewards for policy …

BibTeX
@misc{sun2026twinbridge,
  title = {{TwinBridge: Digital Twin-Driven Policy and Reward Transfer for Real-World Reinforcement Learning in Laboratory Robotics}},
  author = {Shu'ang Sun and Yibo Qiu and Haoliang Ye and Zan Huang and Ao Tian and Kan Ding and Ronald Xu and Mingzhai Sun},
  year = {2026},
  eprint = {2611.06442},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.06442},
}
arXiv cs.RO 2026-11-05 CoRL 2026

OdorSpaces: Visual-Olfactory Embodied Navigation in 3D Environments

Changyeon Lee, Kelin Yu, Zheng Wei, Shuna Ni et al.

Abstract摘要

Olfaction provides critical information about airborne chemical cues, yet it remains largely underexplored in embodied AI, with limited prior machine olfaction work focusing primarily on semantic odor perception. We introduce OdorSpaces, a physics-based simulation platform and benchmark for visual-olfactory embodied navigation. OdorSpaces augments Habitat-Sim with 3D odor transport and dispersion simulated by Fire Dynamics Simulator (FDS), enabling agents to navigate photorealistic indoor environments using both visual and olfactory observations. The benchmark includes two representative …

BibTeX
@misc{lee2026odorspaces,
  title = {{OdorSpaces: Visual-Olfactory Embodied Navigation in 3D Environments}},
  author = {Changyeon Lee and Kelin Yu and Zheng Wei and Shuna Ni and Ruohan Gao},
  year = {2026},
  eprint = {2611.05738},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.05738},
}
arXiv cs.RO 2026-11-04 NeurIPS 2026

LLMs as MDP Designers: A Dependency-Aware Agentic Framework for Automated Robot Policy Generation

Hong Je-Gal, Jinwoo Kim, Chanbin Yi, Hyun-Suk Lee

Abstract摘要

We investigate the automated generation of executable robot reinforcement learning (RL) policies from natural-language task descriptions. Rather than using large language models (LLMs) as execution-time decision makers, we use them as designers that construct RL pipelines before deployment, including Markov decision process (MDP) formulation and simulator implementation. We identify a phase-wise structure in this problem: MDP formulation is dependency-structured and sequential, whereas simulator implementation becomes modular once the formulation is fixed. Based on this structure, we propose …

BibTeX
@misc{jegal2026llms,
  title = {{LLMs as MDP Designers: A Dependency-Aware Agentic Framework for Automated Robot Policy Generation}},
  author = {Hong Je-Gal and Jinwoo Kim and Chanbin Yi and Hyun-Suk Lee},
  year = {2026},
  eprint = {2611.04974},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.04974},
}
arXiv cs.RO 2026-11-04 code

PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations

Travis Davies, Wentao Ma, Lihao Guo, Tengfei Ma et al.

Abstract摘要

A robot world model that serves as a simulator must do more than generate plausible videos: it must faithfully follow commanded actions, maintain consistency across camera views, and sustain coherent long-horizon rollouts. We present PrimeSim, an action-conditioned, multiview world model simulator that addresses these challenges through progressive midtraining and posttraining. Starting from a pretrained video generator, we midtrain on 30,110 hours of robot demonstrations spanning 22 platforms. To improve action following, we introduce a unified cross-embodiment action representation and …

BibTeX
@misc{davies2026primesim,
  title = {{PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations}},
  author = {Travis Davies and Wentao Ma and Lihao Guo and Tengfei Ma and Xiaowen Chang and Jiafeng Xu and Shilong Wang and Yiqi Deng and others},
  year = {2026},
  eprint = {2611.04870},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.04870},
}
arXiv cs.RO 2026-11-04 code

Coordinate Frame Recovery, Per Class NMS and Null Return Modelling for Sim2Real V2X LiDAR Detection

Aman Upganlawar

Abstract摘要

We describe our approach to the V2X-Real track of the UrbanTwin Sim2Real LiDAR Challenge, in which a 3D object detector must be trained exclusively on synthetic data and evaluated on unseen real roadside LiDAR from an Ouster OS1-64 unit, while the synthetic point clouds are simultaneously scored for distributional realism. Our final entry scores 0.7457 combined, from a detection mAP of 0.4382 and a realism score of 0.9251. Three findings account for most of our result, and all three were diagnostic rather than architectural. First, a coordinate frame mismatch between our predictions and the …

BibTeX
@misc{upganlawar2026coordinate,
  title = {{Coordinate Frame Recovery, Per Class NMS and Null Return Modelling for Sim2Real V2X LiDAR Detection}},
  author = {Aman Upganlawar},
  year = {2026},
  eprint = {2611.03940},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.03940},
}
arXiv cs.RO 2026-11-04 code

Geometric Refinement and Distributional Alignment for Sim2Real Roadside LiDAR Detection

Aman Upganlawar

Abstract摘要

We describe our approach to the LUMPI track of the UrbanTwin Sim2Real LiDAR Challenge, in which a 3D object detector must be trained exclusively on synthetic data and evaluated on unseen real roadside LiDAR, while the synthetic point clouds are simultaneously scored for distributional realism. Our final entry scores 0.4793 combined, from a detection mAP of 0.1333 and a realism score of 0.9126. Our contribution is not a new architecture. Working from a PointPillars baseline, we obtained most of our gains from three sources. First, a diagnosis that small object failure in roadside LiDAR is a …

BibTeX
@misc{upganlawar2026geometric,
  title = {{Geometric Refinement and Distributional Alignment for Sim2Real Roadside LiDAR Detection}},
  author = {Aman Upganlawar},
  year = {2026},
  eprint = {2611.03936},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.03936},
}
arXiv cs.RO 2026-11-03 CoRL 2026

KlaskTron-IL: A Contact-Rich Adversarial Imitation Learning Benchmark with a Validated Sim-to-Real Bridge

Nicklas Sohm, Aswin Ramachandran, Raffaello D'Andrea

Abstract摘要

KlaskTron is an open-hardware physical platform for two-player adversarial reinforcement learning, with a learned actuator model that supports zero-shot sim-to-real transfer of trained policies. Building on this platform, we contribute KlaskTron-IL: a multi-tier imitation learning dataset (80k human demonstration timesteps collected directly on the physical robot, 320k symmetry-augmented timesteps, and synthetic expert trajectories up to 5M steps generated by the zero-shot-validated PPO policy), and diagnostic baselines that expose three characteristic failure modes of standard IL methods …

BibTeX
@misc{sohm2026klasktron,
  title = {{KlaskTron-IL: A Contact-Rich Adversarial Imitation Learning Benchmark with a Validated Sim-to-Real Bridge}},
  author = {Nicklas Sohm and Aswin Ramachandran and Raffaello D'Andrea},
  year = {2026},
  eprint = {2611.03091},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.03091},
}
arXiv cs.RO 2026-11-03 code

A Reproducible Reconstruction and Evaluation Framework for Photorealistic Lunar Analog Scene Reconstruction Toward Digital Twins

Antar Mazumder, Ryan Hartzell, Luke Boyd, Alexander Robinson et al.

Abstract摘要

In this paper, we present a reconstruction pipeline that empirically quantifies the photorealistic scene reconstruction accuracy from both human-controlled and rover mast camera monocular feeds against physical ground truth as a function of Lunar traversal effects (e.g., motion blur, haze due to lofted regolith, trajectory bias, and sparse views). First, we benchmark six variants of 3D Gaussian Splatting (3DGS) across three Lunar analog scenes on held-out test sets using standard photometric metrics. We then establish how under traversal effects, this test-set-specific Novel View Synthesis …

BibTeX
@misc{mazumder2026reproducible,
  title = {{A Reproducible Reconstruction and Evaluation Framework for Photorealistic Lunar Analog Scene Reconstruction Toward Digital Twins}},
  author = {Antar Mazumder and Ryan Hartzell and Luke Boyd and Alexander Robinson and Neha Sharma and Chance Carnival and Frances Zhu},
  year = {2026},
  eprint = {2611.00870},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2611.00870},
}
arXiv cs.RO 2026-11-02 code

When the Simulator Fails, Not the Policy: Auditing Contact Artifacts in Simulated Robot Benchmarks

Alex Zhou, Junhao Wu, Xueyang Zhou, Yixiao Huo et al.

Abstract摘要

Simulation benchmarks score robot policies by success rate, and every failed episode counts against the policy. Many of these failures are the simulator's fault, not the policy's; we find the cause and fix it. Testing a vision language action model and a world action model in simulation, we find that the policy often places the object and the simulator then ejects it, and that the benchmark's own scripted demonstrations fail the same way. We present SimuGuard, an auditing plugin for LIBERO, RoboTwin, RoboCasa and RoboDojo. It leaves the evaluation unchanged. At every physics step, it records …

BibTeX
@misc{zhou2026when,
  title = {{When the Simulator Fails, Not the Policy: Auditing Contact Artifacts in Simulated Robot Benchmarks}},
  author = {Alex Zhou and Junhao Wu and Xueyang Zhou and Yixiao Huo and Hongcheng Gao and Di Zhu and Zhenghao Zhang and Yongchao Chen},
  year = {2026},
  eprint = {2610.41857},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.41857},
}
arXiv cs.RO 2026-11-02

$\nabla$Mimic: Ultra-Efficient Humanoid Control with Differentiable Simulation

Weyl Lu, Yubei Chen

Abstract摘要

Robot policy learning is dominated by zeroth-order methods such as PPO, which treat the simulator as a black box and pay for it with enormous sample counts. First-order policy learning differentiates through the dynamics, but on contact-rich whole-body control it has rarely worked: its gradients explode. A recent world-model method showed that derivative information can make humanoid motion tracking far more efficient, using surrogate gradients of a learned model. We show that exact gradients of the simulator itself do better, once two obstacles are removed. Exact gradients contain rare …

BibTeX
@misc{lu2026nabla,
  title = {{$\nabla$Mimic: Ultra-Efficient Humanoid Control with Differentiable Simulation}},
  author = {Weyl Lu and Yubei Chen},
  year = {2026},
  eprint = {2610.41654},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.41654},
}
arXiv cs.CV 2026-11-02

FlowMoDE: Coarse-to-fine Flow Matching for Detail-aware Sim-to-Real Monocular Depth Estimation

Liangjing Shao, Wanhao Liu, Jinsong Lin, Zhiwei Fang et al.

Abstract摘要

Monocular depth estimation is a fundamental capability for 3D spatial perception in robotic and intelligent systems. While data-driven discriminative methods have achieved compelling performance for monocular depth estimation, generative approaches can reconstruct fine structural details with stronger generalization. However, most existing generative diffusion models suffer from low inference efficiency caused by multi-step sampling, whereas single-step diffusion models struggle to recover high-fidelity depth maps. To mitigate these drawbacks, this paper presents FlowMoDE, a coarse-to-fine …

BibTeX
@misc{shao2026flowmode,
  title = {{FlowMoDE: Coarse-to-fine Flow Matching for Detail-aware Sim-to-Real Monocular Depth Estimation}},
  author = {Liangjing Shao and Wanhao Liu and Jinsong Lin and Zhiwei Fang and Hongliang Ren},
  year = {2026},
  eprint = {2610.41190},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2610.41190},
}
arXiv cs.RO 2026-11-02

FlapSim: A Composable MuJoCo Simulation Platform and Reduced-Order Aerodynamic Model Hierarchy for Flapping-Wing Robotics

Mingshan He

Abstract摘要

Flapping-wing simulation must reconcile high-frequency wingbeat aerodynamics with the slower dynamics relevant to flight control and reinforcement learning. We present FlapSim, a modular open-source MuJoCo simulation platform that combines robot descriptions, wing geometry, and composable aerodynamic models in a deterministic simulation pipeline. Across $48$ held-out scenarios spanning frequency, gimbal, wind, frequency-step, gust, and cross-robot flat-plate regimes, we compare five reduced-order configurations operating at $1\,\text{ms}$ with a $50\,\mu\text{s}$ quasi-steady blade-element …

BibTeX
@misc{he2026flapsim,
  title = {{FlapSim: A Composable MuJoCo Simulation Platform and Reduced-Order Aerodynamic Model Hierarchy for Flapping-Wing Robotics}},
  author = {Mingshan He},
  year = {2026},
  eprint = {2610.40902},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.40902},
}
arXiv cs.LG 2026-11-02 code

Frozen in Time: How a Physics Foundation Model Forgets Under Sim-to-Real Adaptation

Haaris Mian, Miles Cranmer, Alessandro Favero, Payel Mukhopadhyay

Abstract摘要

Scientific foundation models (SciFMs) have achieved remarkable performance on a wide range of PDEs, including the ability to efficiently adapt to unseen data distributions with additional finetuning. As with all neural architectures, finetuning such models comes with the risk of catastrophic forgetting, whereby adapting to new tasks degrades prior knowledge of the model. We study catastrophic forgetting in Walrus-1.3B, a SciFM for continuum dynamics, over the course of a two-stage sim-to-real adaptation: first finetuning on simulated flow around a cylinder and then adapting to experimental …

BibTeX
@misc{mian2026frozen,
  title = {{Frozen in Time: How a Physics Foundation Model Forgets Under Sim-to-Real Adaptation}},
  author = {Haaris Mian and Miles Cranmer and Alessandro Favero and Payel Mukhopadhyay},
  year = {2026},
  eprint = {2610.40857},
  archivePrefix = {arXiv},
  primaryClass = {cs.LG},
  url = {https://arxiv.org/abs/2610.40857},
}
arXiv cs.RO 2026-10-30

MUSBRIC: LEGO-Compatible Pneumatic Muscle Bricks for Reconfigurable Musculoskeletal Robots

Qiyao Wang, Yinglei Zhu, Liang Zhou, Wenzhe Gong et al.

Abstract摘要

Musculoskeletal robots combine compliant actuators with articulated skeletons, but exploring alternative configurations often requires repeated fabrication. We present MUSBRIC, a modular hardware platform and accompanying MuJoCo-based simulator for reconfigurable musculoskeletal robots. LEGO-compatible endcaps turn fiber-reinforced extensile pneumatic artificial muscles into reusable, plug-and-play muscle bricks that connect directly to standard LEGO components. Experimentally identified actuator behavior supports corresponding musculoskeletal simulations. An elbow-joint prototype validates …

BibTeX
@misc{wang2026musbric,
  title = {{MUSBRIC: LEGO-Compatible Pneumatic Muscle Bricks for Reconfigurable Musculoskeletal Robots}},
  author = {Qiyao Wang and Yinglei Zhu and Liang Zhou and Wenzhe Gong and Xin-Jun Liu and Huichan Zhao},
  year = {2026},
  eprint = {2610.40285},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.40285},
}
arXiv cs.RO 2026-10-30

SimRetract: Zero-Shot Sim-to-Real Robotic Assistance for Retractor Take-Over in Open Surgery

Xucheng Wang, Zhizhou Yang, Sung Eun Kim, Romain Hardy et al.

Abstract摘要

We demonstrate the first zero-shot sim-to-real transfer for a surgeon-robot collaboration task in open surgery: retractor take-over. A robot arm takes a retractor from the surgeon's hand and preserves retraction at handoff, using a policy trained only on simulated demonstrations, without human demonstrations or real-world fine-tuning. Imitation learning from real demonstrations is limited by collection and labeling costs, and by performance degradation when the environment changes. Our framework, SimRetract, generates simulated demonstrations designed for transfer: the policy observes masked …

BibTeX
@misc{wang2026simretract,
  title = {{SimRetract: Zero-Shot Sim-to-Real Robotic Assistance for Retractor Take-Over in Open Surgery}},
  author = {Xucheng Wang and Zhizhou Yang and Sung Eun Kim and Romain Hardy and Michael P. Sampson and Aakash Reddy and Ankit Pal and Xiaoman Zhang and others},
  year = {2026},
  eprint = {2610.38234},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.38234},
}
arXiv cs.AI 2026-10-30 code WACV 2027

Wavelet Phase Diffusion for Structurally and Semantically Consistent Sim-to-Real Translation

Kaiwen Wang, Frank Bieder, Yinzhe Shen, Carlos Fernandez et al.

Abstract摘要

Simulation-to-reality translation must bridge the appearance gap between synthetic and real domains while preserving structural and semantic consistency. Conditioning-based methods achieve spatial alignment but introduce computationally expensive control modules. Paired-data methods achieve realism but rely on complex synthesis pipelines, often altering scene geometry and semantics. Training-free editing methods avoid both constraints but lack a learned appearance prior, limiting their perceptual quality. Recently proposed phase-preserving diffusion presents a promising alternative, but …

BibTeX
@misc{wang2026wavelet,
  title = {{Wavelet Phase Diffusion for Structurally and Semantically Consistent Sim-to-Real Translation}},
  author = {Kaiwen Wang and Frank Bieder and Yinzhe Shen and Carlos Fernandez and Jan-Hendrik Pauls and Omer Sahin Tas},
  year = {2026},
  eprint = {2607.21628},
  archivePrefix = {arXiv},
  primaryClass = {cs.AI},
  url = {https://arxiv.org/abs/2607.21628},
}
arXiv cs.RO 2026-10-28 code

Rendering-Free Event Frame Simulation for Fast Reinforcement Learning of Autonomous Robot Navigation

Dequan Ou, Austin Lopez, Quentin Missinne, Christophe De Wagter et al.

Abstract摘要

Event cameras offer low latency, high dynamic range, and milliwatt-level power consumption, making them ideal for agile robots such as tiny drones navigating through cluttered environments. However, existing simulators generally render photorealistic images before converting them into events, making large-scale reinforcement learning prohibitively slow. We propose an analytic event simulator that exploits what event cameras fundamentally measure - moving contrast edges - to synthesize event streams directly from scene geometry and ego-motion without visual rendering. Our simulator generates a …

BibTeX
@misc{ou2026rendering,
  title = {{Rendering-Free Event Frame Simulation for Fast Reinforcement Learning of Autonomous Robot Navigation}},
  author = {Dequan Ou and Austin Lopez and Quentin Missinne and Christophe De Wagter and Guido C. H. E. de Croon},
  year = {2026},
  eprint = {2610.37543},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.37543},
}
arXiv cs.RO 2026-10-28 code

AuRaSim: A Ray-Tracing Based Automotive FMCW Radar Simulator for Dynamic Scenarios

Zhaoze Wang, Changxu Zhang, Tai Fei, Christopher Grimm et al.

Abstract摘要

Modern simulators can generate synthetic camera and LiDAR data with accurate annotations for downstream tasks. In contrast, automotive radar simulation remains less mature because it requires not only a 3D engine to model dynamic objects in the scenes but also electromagnetic material properties, antenna configurations, wave propagation mechanisms, and coherent signal synthesis. Existing frameworks are either proprietary or overly simplified, limiting the scalability of radar raw measurements. This paper presents AuRaSim, a ray-tracing-based automotive frequency-modulated continuous wave …

BibTeX
@misc{wang2026aurasim,
  title = {{AuRaSim: A Ray-Tracing Based Automotive FMCW Radar Simulator for Dynamic Scenarios}},
  author = {Zhaoze Wang and Changxu Zhang and Tai Fei and Christopher Grimm and Yi Jin and Claas Tebruegge and Markus Gardill},
  year = {2026},
  eprint = {2610.37403},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.37403},
}
arXiv cs.RO 2026-10-28

ActiveAlign: Aligning Egocentric Manipulation via Active Perception

Ri-Zhao Qiu, Bowen Wen, Yifeng Jiang, Chen Tessler et al.

Abstract摘要

Real-to-Sim-to-Real (Real2Sim2Real) enables structured world representations for planning, interpretability, and safe execution. Most existing approaches rely on passive perception, which creates real2sim gaps due to imperfect observation. Inspired by how humans perceive actively through actions, we propose ActiveAlign, a framework that leverages active perception to align the Real2Sim2Real gap from interactions. ActiveAlign introduces two complementary modules: (i) ActiveAlign-Waving, which performs hand-eye calibration by exploiting active hand motions and differentiable rendering, and (ii) …

BibTeX
@misc{qiu2026activealign,
  title = {{ActiveAlign: Aligning Egocentric Manipulation via Active Perception}},
  author = {Ri-Zhao Qiu and Bowen Wen and Yifeng Jiang and Chen Tessler and Eric Heiden and Xue Bin Peng and Xiaolong Wang and Stan Birchfield and others},
  year = {2026},
  eprint = {2610.36859},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.36859},
}
arXiv cs.CV 2026-10-28 code

SO-101 Bench: Accessible Spatial Manipulation

Truman Hickok

Abstract摘要

Low-cost arms such as the SO-101 have become the most common entry point to robot learning, yet no released policy performs spatially constrained, language-conditioned tasks on them out of the box, and existing SO-101 benchmarks run only on physical hardware with simple tasks and few held-out objects. We introduce SO-101 Bench, a simulated benchmark for language-conditioned spatial manipulation built on an Isaac Lab digital twin of a real SO-101 setup. It has four tasks scored as five families, 138 objects in seen, unseen-instance and unseen-class splits, 916 evaluation episodes with subsets …

BibTeX
@misc{hickok2026so,
  title = {{SO-101 Bench: Accessible Spatial Manipulation}},
  author = {Truman Hickok},
  year = {2026},
  eprint = {2610.36420},
  archivePrefix = {arXiv},
  primaryClass = {cs.CV},
  url = {https://arxiv.org/abs/2610.36420},
}
arXiv cs.RO 2026-10-27 code

Zero-HLM: Generalizable Humanoid Loco-Manipulation without Real Robot Data

Dianyi Yang, Mengya Liu, Zhumei Wang, Yu Liu et al.

Abstract摘要

Learning generalizable humanoid loco-manipulation remains bottlenecked by costly real-world demonstrations. Simulation provides a scalable alternative, but requires visually faithful, physics-ready scenes and executable whole-body motions. We present Zero-HLM, a real-to-sim-to-real framework that transforms smartphone captures and simulated source demonstrations into scalable training data for humanoid loco-manipulation. Gaussian-guided agentic real-to-sim reconstruction aligns visual and physical scenes; motion-environment co-adaptation uses rollout feedback to correct whole-body references …

BibTeX
@misc{yang2026zero,
  title = {{Zero-HLM: Generalizable Humanoid Loco-Manipulation without Real Robot Data}},
  author = {Dianyi Yang and Mengya Liu and Zhumei Wang and Yu Liu and Xiaochen Zhang and Yixuan Li and Le Ma and Yuhang Yang and others},
  year = {2026},
  eprint = {2610.35075},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.35075},
}
arXiv cs.RO 2026-10-27

EAST: Embodied AI Safety Testing via Systematic Fault Injection in Digital Twins

Yuhao Tian, Tao Li, Ling Zhou, Dave Towey et al.

Abstract摘要

Task success is not a sufficient measure of safety for embodied artificial intelligence (AI), because robots may complete objectives while violating safety requirements. Existing evaluations often emphasize performance and robustness, but lack a systematic route from documented safety hazards to executable, verifiable tests. We present EAST (Embodied AI Safety Testing), a digital-twin framework that converts literature-grounded safety evidence into fault-injection tests across perception, instructions, environments, actions, and timing. EAST combines an expert-reviewed safety-fault taxonomy …

BibTeX
@misc{tian2026east,
  title = {{EAST: Embodied AI Safety Testing via Systematic Fault Injection in Digital Twins}},
  author = {Yuhao Tian and Tao Li and Ling Zhou and Dave Towey and Zhaoxin Fan and Wenjun Wu and Rubing Huang and Tsong Yueh Chen},
  year = {2026},
  eprint = {2610.34358},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.34358},
}
arXiv cs.RO 2026-10-27

Learning Interaction-Aware Path Corrections from Unlabeled Trajectories: A LiDAR-Based Sim-to-Real GNN Framework for Construction Robots

Yilong Chen, Yong K. Cho

Abstract摘要

Construction robots operating near workers require navigation that can anticipate human motion while remaining robust to dynamic and unstructured site conditions. However, existing social navigation methods depend on hand-crafted interaction rules, labeled demonstrations, or robot-specific control policies, limiting their scalability and transferability in construction environments. We propose a real-time, LiDAR-only framework that learns interaction-aware path corrections from unlabeled demonstrations. Constant-velocity extrapolation generates residual learning targets, while a GNN models …

BibTeX
@misc{chen2026learning,
  title = {{Learning Interaction-Aware Path Corrections from Unlabeled Trajectories: A LiDAR-Based Sim-to-Real GNN Framework for Construction Robots}},
  author = {Yilong Chen and Yong K. Cho},
  year = {2026},
  eprint = {2610.34060},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.34060},
}
arXiv cs.RO 2026-10-27

Learning Dexterous Manipulation: Hands, Simulators, Training, and Evaluation

Luai Abuelsamen

Abstract摘要

A dexterous hand can change an object's pose without setting it down. This survey covers 113 learning-based methods that attempt it, the hands they run on, the simulators they train in, and how they report results. The field has largely converged on one recipe: reinforcement learning on privileged state in a GPU simulator, distilled into a vision-only student for transfer to hardware. Almost half the corpus trains that way, nearly all of it in one simulator, whose own successors are barely used. A second and faster-growing branch learns from teleoperated demonstration instead, through …

BibTeX
@misc{abuelsamen2026learning,
  title = {{Learning Dexterous Manipulation: Hands, Simulators, Training, and Evaluation}},
  author = {Luai Abuelsamen},
  year = {2026},
  eprint = {2610.33486},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.33486},
}
arXiv cs.RO 2026-10-26

Regularised RL improves sim-to-real transfer

Danilo Vucetic, Mohamad H. Danesh, Florence Clerc, Hsiu-Chin Lin et al.

Abstract摘要

Regularised reinforcement learning (RL) has provable robustness guarantees that should ease the transfer of policies from simulation to robots, known as sim-to-real. Yet, weakly regularised algorithms like Proximal Policy Optimisation (PPO) remain the de facto choice in sim-to-real pipelines, while the practical benefits of regularisation for transfer remain poorly characterised. In this work, we study the sim-to-real performance of commonly used RL algorithms, with the aim of characterising the effects of regularisation on robotic performance. To that end, we derive Soft MellowMax …

BibTeX
@misc{vucetic2026regularised,
  title = {{Regularised RL improves sim-to-real transfer}},
  author = {Danilo Vucetic and Mohamad H. Danesh and Florence Clerc and Hsiu-Chin Lin and Jonathan Tremblay},
  year = {2026},
  eprint = {2610.32855},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.32855},
}
arXiv cs.RO 2026-10-26

Delay Randomization Widens the Delay Margin of Learned Humanoid Motion Trackers

Shaoqin Li, Yi Sun

Abstract摘要

Learned humanoid controllers are usually trained in one simulator and then checked in a second one before they go near hardware. We ask what that check says about command delay. We train motion-tracking policies for a 24-joint humanoid on five motions taken from monocular video and test them in an independent CPU MuJoCo harness, which we first verify against the training model. Every policy completes its motion in at least 26 of 30 episodes under the training randomization. With 40 ms of constant command delay, however, survival drops to 15% on average (0% - 45%), and the delay margin is only …

BibTeX
@misc{li2026delay,
  title = {{Delay Randomization Widens the Delay Margin of Learned Humanoid Motion Trackers}},
  author = {Shaoqin Li and Yi Sun},
  year = {2026},
  eprint = {2610.32277},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.32277},
}
arXiv cs.RO 2026-10-26

WorldMirror: Agentic Real-to-Sim Generation of Interactive Worlds from In-the-Wild Robot Demonstrations

Tianling Xu, Weijie Wan, Honghao Su, Kailun Su et al.

Abstract摘要

Existing approaches for robot learning in simulation often require substantial manual effort to construct scenes and specify tasks, limiting training scalability and data diversity. Meanwhile, in-the-wild robot demonstrations naturally provide diverse and realistic observations of real-world interactions. Leveraging these demonstrations for simulation requires both high-fidelity visual reconstruction and physically consistent interactions. General-purpose agents offer flexible adaptation to diverse scenarios and strong reasoning about 3D spatial relationships, while specialized generative …

BibTeX
@misc{xu2026worldmirror,
  title = {{WorldMirror: Agentic Real-to-Sim Generation of Interactive Worlds from In-the-Wild Robot Demonstrations}},
  author = {Tianling Xu and Weijie Wan and Honghao Su and Kailun Su and Junyuan Tang and Huichi Zhou and Haozheng Zhang and Qi Xiong and others},
  year = {2026},
  eprint = {2610.31834},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.31834},
}
arXiv cs.RO 2026-10-23

TerraTransfer++: Demonstration-Free End-to-End Planner

Zikang Xiong, Weixin Li, Zhouchonghao Wu, Akshay Rangesh et al.

Abstract摘要

End-to-end autonomous driving has achieved state-of-the-art performance on benchmarks and real-world deployments. Its standard training recipe, however, is expensive across all existing paradigms: imitation learning requires fleet-scale driving logs whose behavior distribution only thinly covers the safety-critical tail; closed-loop reinforcement learning in a photorealistic simulator, while offering diverse behaviors, is bottlenecked by sample-efficiency, per-step cost of rendering, and a forward pass through a large vision backbone. Self-play in vectorized simulators changes the economics: …

BibTeX
@misc{xiong2026terratransfer,
  title = {{TerraTransfer++: Demonstration-Free End-to-End Planner}},
  author = {Zikang Xiong and Weixin Li and Zhouchonghao Wu and Akshay Rangesh and Saarth Bonde and Grantland Hall and Chen Tang and Yihan Hu and others},
  year = {2026},
  eprint = {2610.30319},
  archivePrefix = {arXiv},
  primaryClass = {cs.RO},
  url = {https://arxiv.org/abs/2610.30319},
}