Visual / LiDAR SLAM and odometry, 3D reconstruction, object pose, depth and open-vocabulary scene maps for robots.视觉/激光 SLAM 与里程计、三维重建、物体位姿、深度估计与开放词汇场景地图。
The go-to feature-based SLAM library — monocular, stereo and RGB-D, with IMU fusion and multi-map relocalization.最常用的特征点 SLAM 库：支持单目、双目与 RGB-D，可融合 IMU，并支持多地图重定位。
@misc{campos2020orb,
title = {{ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM}},
author = {Carlos Campos and Richard Elvira and Juan J. Gómez Rodríguez and José M. M. Montiel and Juan D. Tardós},
year = {2020},
eprint = {2007.11898},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2007.11898},
}
SAM — a promptable segmentation model (points, boxes, masks) trained on 1B+ masks; a standard building block for object masks in robot perception pipelines.SAM：可用点、框、掩码提示的分割模型，在 10 亿级掩码上训练；已成为机器人感知流程中获取物体掩码的常用基础组件。
@misc{kirillov2023segment,
title = {{Segment Anything}},
author = {Alexander Kirillov and Eric Mintun and Nikhila Ravi and Hanzi Mao and Chloe Rolland and Laura Gustafson and Tete Xiao and Spencer Whitehead and Alexander C. Berg and Wan-Yen Lo and Piotr Dollár and Ross Girshick},
year = {2023},
eprint = {2304.02643},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2304.02643},
}
NISE targets the sharp failure of 3D policies under realistic depth noise, carrying position uncertainty into attention; tested on transparent and reflective objects with commodity RGB-D.NISE 针对 3D 策略在真实深度噪声下的急剧失效，把位置不确定性带入注意力计算；在透明和反光物体上用普通 RGB-D 相机测试。
@misc{yang2026noise,
title = {{Noise-Invariant Spatial Encoding for 3D Manipulation Policies under Depth Corruption}},
author = {Zhiyuan Yang and Jiaju He and Ruiteng Zhao and Anqi Cheng and Haiyue Zhu and Kezhi Mao},
year = {2026},
eprint = {2610.24674},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2610.24674},
}
One feed-forward transformer predicts cameras, depth, point maps and tracks for many views at once, in about a second.单个前馈 Transformer 一次性为多视角图像预测相机参数、深度、点图与跟踪，约一秒完成。
@misc{wang2025vggt,
title = {{VGGT: Visual Geometry Grounded Transformer}},
author = {Jianyuan Wang and Minghao Chen and Nikita Karaev and Andrea Vedaldi and Christian Rupprecht and David Novotny},
year = {2025},
eprint = {2503.11651},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2503.11651},
}
Stereo depth model trained on large synthetic data that reports strong zero-shot accuracy on real scenes — a drop-in depth source for stereo-camera robots.在大规模合成数据上训练的双目深度模型，报告称在真实场景上零样本精度很强；可直接作为双目相机机器人的深度来源。
@misc{wen2025foundationstereo,
title = {{FoundationStereo: Zero-Shot Stereo Matching}},
author = {Bowen Wen and Matthew Trepte and Joseph Aribido and Jan Kautz and Orazio Gallo and Stan Birchfield},
year = {2025},
eprint = {2501.09898},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2501.09898},
}
Segments and tracks every instance of a concept given a short noun phrase or image exemplar, in images and video; trained with a data engine covering 4M concept labels, with open weights and the SA-Co benchmark.给定短名词短语或示例图像，即可在图像和视频中分割并跟踪某一概念的所有实例；数据引擎覆盖 400 万个概念标签，开放权重与 SA-Co 基准，可直接用作机器人开放词汇感知模块。
@misc{carion2025sam,
title = {{SAM 3: Segment Anything with Concepts}},
author = {Nicolas Carion and Laura Gustafson and Yuan-Ting Hu and Shoubhik Debnath and Ronghang Hu and Didac Suris and Chaitanya Ryali and Kalyan Vasudev Alwala and Haitham Khedr and Andrew Huang and Jie Lei and Tengyu Ma and Baishan Guo and Arpit Kalla and Markus Marks and Joseph Greer and Meng Wang and Peize Sun and Roman Rädle and Triantafyllos Afouras and Effrosyni Mavroudi and Katherine Xu and Tsung-Han Wu and Yu Zhou and Liliane Momeni and Rishi Hazra and Shuangrui Ding and Sagar Vaze and Francois Porcher and Feng Li and Siyuan Li and Aishwarya Kamath and Ho Kei Cheng and Piotr Dollár and Nikhila Ravi and Kate Saenko and Pengchuan Zhang and Christoph Feichtenhofer},
year = {2025},
eprint = {2511.16719},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2511.16719},
}
Monocular depth model trained on tens of millions of pseudo-labelled images; a common off-the-shelf depth prior for robots.在数千万张伪标注图像上训练的单目深度模型，常被机器人系统直接拿来作为深度先验。
@misc{yang2024depth,
title = {{Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data}},
author = {Lihe Yang and Bingyi Kang and Zilong Huang and Xiaogang Xu and Jiashi Feng and Hengshuang Zhao},
year = {2024},
eprint = {2401.10891},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2401.10891},
}
Extends SAM to video with a streaming memory, so a mask prompted once is tracked across frames — handy for following objects during manipulation.用流式记忆把 SAM 扩展到视频：一次提示得到的掩码可在后续帧中持续跟踪，适合在操作过程中跟随目标物体。
@misc{ravi2024sam,
title = {{SAM 2: Segment Anything in Images and Videos}},
author = {Nikhila Ravi and Valentin Gabeur and Yuan-Ting Hu and Ronghang Hu and Chaitanya Ryali and Tengyu Ma and Haitham Khedr and Roman Rädle and Chloe Rolland and Laura Gustafson and Eric Mintun and Junting Pan and Kalyan Vasudev Alwala and Nicolas Carion and Chao-Yuan Wu and Ross Girshick and Piotr Dollár and Christoph Feichtenhofer},
year = {2024},
eprint = {2408.00714},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2408.00714},
}
Extends DUSt3R with a dense local-feature head, so one network gives both 3D pointmaps and accurate pixel matches between views — useful for calibration-free reconstruction and localization.在 DUSt3R 基础上加入稠密局部特征头，同一网络既输出三维点图又给出视角间精确的像素匹配，适用于免标定的三维重建与定位。
FAST-LIVO2 — fuses LiDAR, camera and IMU in one filter with direct (feature-free) updates for both sensors, sharing a single voxel map where image patches are attached to LiDAR points.FAST-LIVO2：在同一滤波器中融合激光雷达、相机与 IMU，两种传感器都采用直接法（无需提取特征）更新，并共用一张体素地图，图像块挂载在激光点上。
@misc{zheng2024fast,
title = {{FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry}},
author = {Chunran Zheng and Wei Xu and Zuhao Zou and Tong Hua and Chongjian Yuan and Dongjiao He and Bingyang Zhou and Zheng Liu and Jiarong Lin and Fangcheng Zhu and Yunfan Ren and Rong Wang and Fanle Meng and Fu Zhang},
year = {2024},
eprint = {2408.14035},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2408.14035},
}
Trains a large teacher only on synthetic images with precise depth, then pseudo-labels many real images to train smaller students; gives sharper, more robust monocular depth than V1.先只用深度精确的合成图像训练大教师模型，再给大量真实图像打伪标签来训练小模型；单目深度比 V1 更锐利、更鲁棒。
@misc{yang2024depth,
title = {{Depth Anything V2}},
author = {Lihe Yang and Bingyi Kang and Zilong Huang and Zhen Zhao and Xiaogang Xu and Jiashi Feng and Hengshuang Zhao},
year = {2024},
eprint = {2406.09414},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2406.09414},
}
MonoGS — runs SLAM directly on a 3D Gaussian map, giving camera tracking and a photorealistic dense map from one camera.MonoGS：直接在三维高斯地图上做 SLAM，仅用单个相机即可同时完成相机跟踪与照片级稠密建图。
@misc{matsuki2023gaussian,
title = {{Gaussian Splatting SLAM}},
author = {Hidenobu Matsuki and Riku Murai and Paul H. J. Kelly and Andrew J. Davison},
year = {2023},
eprint = {2312.06741},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2312.06741},
}
Regresses 3D point maps straight from image pairs without known camera intrinsics or poses; started the "3D foundation model" wave.不需要已知相机内参或位姿，直接从图像对回归三维点图，开启了“三维基础模型”这一方向。
@misc{wang2023dust,
title = {{DUSt3R: Geometric 3D Vision Made Easy}},
author = {Shuzhe Wang and Vincent Leroy and Yohann Cabon and Boris Chidlovskii and Jerome Revaud},
year = {2023},
eprint = {2312.14132},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2312.14132},
}
6D pose estimation and tracking of unseen objects from a CAD model or a few reference images, with no per-object training.只需 CAD 模型或少量参考图像即可对未见过的物体做 6D 位姿估计与跟踪，无需逐物体训练。
@misc{wen2023foundationpose,
title = {{FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects}},
author = {Bowen Wen and Wei Yang and Jan Kautz and Stan Birchfield},
year = {2023},
eprint = {2312.08344},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2312.08344},
}
Open-set detector that finds objects from a free-text prompt; often paired with SAM ("Grounded-SAM") to turn a language instruction into object masks.开放集目标检测器，可根据任意文本提示找到物体；常与 SAM 组合（Grounded-SAM），把语言指令变成物体掩码。
@misc{liu2023grounding,
title = {{Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection}},
author = {Shilong Liu and Zhaoyang Zeng and Tianhe Ren and Feng Li and Hao Zhang and Jie Yang and Qing Jiang and Chunyuan Li and Jianwei Yang and Hang Su and Jun Zhu and Lei Zhang},
year = {2023},
eprint = {2303.05499},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2303.05499},
}
Self-supervised image features that work frozen for depth, segmentation and retrieval; a common visual backbone in VLAs (e.g. OpenVLA) and latent world models.自监督学习的图像特征，冻结即可用于深度估计、分割和检索；是 VLA（如 OpenVLA）和潜空间世界模型常用的视觉骨干。
@misc{oquab2023dinov,
title = {{DINOv2: Learning Robust Visual Features without Supervision}},
author = {Maxime Oquab and Timothée Darcet and Théo Moutakanni and Huy Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El-Nouby and Mahmoud Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po-Yao Huang and Shang-Wen Li and Ishan Misra and Michael Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Hervé Jegou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski},
year = {2023},
eprint = {2304.07193},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2304.07193},
}
Transformer that tracks many video points jointly rather than one at a time, staying robust through occlusions; widely used to extract motion tracks from human or robot videos for policy learning.联合跟踪视频中大量点（而非逐点独立跟踪）的 Transformer，遮挡下依然稳健；常用于从人类或机器人视频中提取运动轨迹来学习策略。
@misc{karaev2023cotracker,
title = {{CoTracker: It is Better to Track Together}},
author = {Nikita Karaev and Ignacio Rocco and Benjamin Graham and Natalia Neverova and Andrea Vedaldi and Christian Rupprecht},
year = {2023},
eprint = {2307.07635},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2307.07635},
}
Tracks the 6-DoF pose of a never-seen object in RGB-D video while building its neural 3D model online, with no CAD model needed; useful for manipulating novel objects.在 RGB-D 视频中跟踪从未见过物体的六自由度位姿，同时在线构建其神经三维模型，无需 CAD 模型；适用于操作新物体。
@misc{wen2023bundlesdf,
title = {{BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects}},
author = {Bowen Wen and Jonathan Tremblay and Valts Blukis and Stephen Tyree and Thomas Muller and Alex Evans and Dieter Fox and Jan Kautz and Stan Birchfield},
year = {2023},
eprint = {2303.14158},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2303.14158},
}
AnyGrasp — dense 7-DoF parallel-gripper grasp detection trained on real sensor data with analytic labels and center-of-mass awareness, plus grasp tracking across frames for moving objects; released as an SDK.AnyGrasp：基于真实传感器数据与解析标注训练、考虑物体质心的稠密 7 自由度平行夹爪抓取检测，并能跨帧跟踪抓取以应对运动物体；以 SDK 形式发布。
@misc{fang2022anygrasp,
title = {{AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains}},
author = {Hao-Shu Fang and Chenxi Wang and Hongjie Fang and Minghao Gou and Jirong Liu and Hengxu Yan and Wenhai Liu and Yichen Xie and Cewu Lu},
year = {2022},
eprint = {2212.08333},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2212.08333},
}
Registers raw LiDAR points directly to the map with an incremental k-d tree; fast enough for onboard drone and robot computers.用增量 k-d 树把原始激光点直接配准到地图，速度足以在无人机和机器人机载计算机上运行。
@misc{xu2021fast,
title = {{FAST-LIO2: Fast Direct LiDAR-inertial Odometry}},
author = {Wei Xu and Yixi Cai and Dongjiao He and Jiarong Lin and Fu Zhang},
year = {2021},
eprint = {2107.06829},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2107.06829},
}
@misc{teed2021droid,
title = {{DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras}},
author = {Zachary Teed and Jia Deng},
year = {2021},
eprint = {2108.10869},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2108.10869},
}
@misc{shan2020lio,
title = {{LIO-SAM: Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping}},
author = {Tixiao Shan and Brendan Englot and Drew Meyers and Wei Wang and Carlo Ratti and Daniela Rus},
year = {2020},
eprint = {2007.00258},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2007.00258},
}
Open C++ library for real-time metric-semantic visual-inertial SLAM: VIO, robust pose graph, fast 3D mesher and dense semantic reconstruction as modular parts.开源 C++ 实时度量-语义视觉惯性 SLAM 库，模块化包含 VIO、鲁棒位姿图、快速三维网格与稠密语义重建。
@misc{rosinol2019kimera,
title = {{Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping}},
author = {Antoni Rosinol and Marcus Abate and Yun Chang and Luca Carlone},
year = {2019},
eprint = {1910.02490},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/1910.02490},
}
RGB-D scans of 1,500+ indoor scenes with 3D reconstructions, camera poses and semantic labels; the standard benchmark for 3D scene understanding that embodied perception builds on.1500+ 个室内场景的 RGB-D 扫描，含三维重建、相机位姿与语义标注；具身感知所依赖的三维场景理解标准基准。
@misc{dai2017scannet,
title = {{ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes}},
author = {Angela Dai and Angel X. Chang and Manolis Savva and Maciej Halber and Thomas Funkhouser and Matthias Nießner},
year = {2017},
eprint = {1702.04405},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/1702.04405},
}
Open spatiotemporal embodied foundation models (2B, 8B, 30B-A3B MoE) for egocentric understanding, localization, grounded reasoning and planning, plus post-trained Nav, Plan, VLA and CoP variants.开源时空具身基础模型（2B、8B 与 30B-A3B MoE），覆盖第一视角理解、时空定位、物理落地推理与规划，并提供导航、规划、VLA、CoP 等后训练版本。
@misc{dang2026rynnbrain,
title = {{RynnBrain: Open Embodied Foundation Models}},
author = {Ronghao Dang and Jiayan Guo and Bohan Hou and Sicong Leng and Kehan Li and Xin Li and Jiangpin Liu and Yunxuan Mao and Zhikai Wang and Yuqian Yuan and Minghao Zhu and Xiao Lin and Yang Bai and Qian Jiang and Yaxi Zhao and Minghua Zeng and Junlong Gao and Yuming Jiang and Jun Cen and Siteng Huang and Liuyi Wang and Wenqiao Zhang and Chengju Liu and Jianfei Yang and Shijian Lu and Deli Zhao},
year = {2026},
eprint = {2602.14979},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2602.14979},
}
Renders wrist-camera views from a 3D Gaussian Splatting scan of the real workspace to fine-tune π0.5 for precise reaching in e-waste disassembly; reports 80% vs. 58.7% with 150 teleop demos.用真实工作台的 3D 高斯泼溅重建渲染腕部相机训练视角，微调 π0.5 以完成电子垃圾拆解中的精确抵达；报告成功率 80%，而 150 条遥操作示教为 58.7%，人工采集不到 10 分钟。
Fingertip sensor whose one camera switches illumination to alternate between see-through-membrane vision and tactile images — one shared viewpoint, no extrinsic calibration; fused by a transformer (VisTacFusion).指尖传感器只用一个摄像头，通过切换照明交替获取“透过膜的视觉图像”和触觉图像，视觉与触觉共享同一视角、无需相机外参标定；再用 Transformer（VisTacFusion）融合两者。
@misc{wang2026gelslim,
title = {{GelSlim 5.0: Unifying Vision and Touch with a Single Fingertip Camera}},
author = {Xiangdong Wang and I-Hsuan Huang and Xiaohao Xu and Xili Yi and Nima Fazeli and Xiaonan Huang},
year = {2026},
eprint = {2610.31334},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2610.31334},
}
A lightweight foothold prediction model strips terrain irrelevant to the next steps from the elevation map before the humanoid policy sees it, aiming at faster training and better transfer to new terrain.不再把整张高程图输入人形机器人运动策略，而是先用轻量的落脚点预测模型去掉与接下来几步无关的地形信息，以加快训练并提升对新地形的泛化。
@misc{heyrman2026watch,
title = {{Watch Your Step: Anticipated Perception for Humanoid Locomotion}},
author = {Matthias Heyrman and Chenhao Li and Ioannis Dadiotis and Marco Hutter},
year = {2026},
eprint = {2610.29612},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2610.29612},
}
A quadruped solves a giant Rubik's Cube with its feet: onboard RGB-D estimates cube pose and colours, a planner sequences skills, and RL whole-body skills turn layers. Reports three full autonomous solves.四足机器人只用脚完成巨型魔方：机载 RGB-D 估计魔方位姿与颜色状态，规划器把解法转成技能序列，强化学习训练的全身技能负责翻转魔方、一脚固定一脚推动转层。报告完成三次完全自主求解。
@misc{amiet2026solving,
title = {{Solving a Giant Rubik's Cube with a Quadruped Robot}},
author = {Lukas Amiet and Gabriel Sánchez-Blanco Repgen and Mayank Mittal and Victor Klemm and Andrei Cramariuc and Marco Hutter and Cesar Cadena},
year = {2026},
eprint = {2610.24610},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2610.24610},
}
Adds exteroceptive sensing to whole-body motion tracking, so a humanoid performs dynamic non-locomotion skills on uneven terrain.将外部感知融入全身动作跟踪，让人形机器人在不平整地形上完成高动态的非行走类技能。
An end-to-end perceptive framework mapping depth to control for humanoid hiking over diverse unstructured terrain.端到端感知框架，将深度输入映射到控制，实现人形机器人在多样非结构化地形上徒步。
@misc{zhu2026hiking,
title = {{Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoids}},
author = {Shaoting Zhu and Ziwen Zhuang and Mengjie Zhao and Kun-Ying Lee and Hang Zhao},
year = {2026},
eprint = {2601.07718},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2601.07718},
}
Self-supervised foot-contact estimation from joint encoders and IMU only, fed as a stance belief into a Kalman filter. Reports the lowest leg-odometry error among the compared baselines.仅用关节编码器与 IMU 自监督估计足端接触，并作为支撑置信度输入卡尔曼滤波器。报告腿式里程计误差在对比方法中最低。
A 16B model interleaving video prediction and language reasoning for embodied understanding and long-horizon visual planning, plus a world-action extension for control; reports 51.5% on 20 RoboCasa365 tasks.16B 统一具身模型，交替进行视频预测与语言推理，兼顾具身理解与长程视觉规划，并扩展出用于机器人控制的世界-动作版本；另提出 Rynn-VP、Rynn-GEU 评测，报告在 20 个 RoboCasa365 组合任务上成功率 51.5%。
@misc{zhu2026rynnunify,
title = {{RynnUnify: Towards Unified Embodied Brain}},
author = {Minghao Zhu and Bohan Hou and Kun Xiang and Zixuan Wang and Yinzhou Tang and Yifei Yang and Zhikai Wang and Tianyi Zhang and Kehan Li and Haoyu Zhao and Siteng Huang and Leigang Qu and Sicong Leng and Dongchi Huang and Mingxiu Chen and Shijian Lu and Yue Wang and Xiaodan Liang and Zhenyu Zeng and Deli Zhao and Chengju Liu and Jianfei Yang and Xin Li},
year = {2026},
eprint = {2610.32965},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2610.32965},
}
GEMS keeps a 3D Gaussian Splatting map that is updated only where the scene changes, and an agent renders views on demand to answer when/where questions. Introduces GEMS-Bench (15 scenes, 473 QA pairs).GEMS 维护一张只在场景变化处增量更新的 3DGS 地图，智能体按需渲染新视角来回答时空问题和定位物体；同时发布 GEMS-Bench（3 个真实 + 12 个合成环境，473 个问答对），报告在物体定位和时空问答上优于近期基线。
@misc{chen2026gaussian,
title = {{Gaussian Episodic Memory for Long-Term Spatiotemporal Reasoning}},
author = {Ling-Chia Chen and Abdelrhman Werby and Kaan Aytekin and Kai O. Arras},
year = {2026},
eprint = {2610.33158},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2610.33158},
}
A sparse-voxel radiance map built from LiDAR and camera data, aimed at robot logs — few viewpoints, imperfect poses and large scenes — while keeping geometry accurate and GPU memory in check.用激光雷达与相机数据构建稀疏体素辐射场地图，针对机器人数据视角少、位姿有误差、场景大的问题，在保证几何精度的同时控制显存占用。
@misc{liu2026sparv,
title = {{SpaRV: Sparse Radiance Voxels for Scalable Geometrically Consistent LiDAR-Visual Mapping and Rendering}},
author = {Jianheng Liu and Yunfei Wan and Fangming Cheng and Xiangyu Hong and Zuhao Zou and Haotian Li and Longji Yin and Chunran Zheng and Jiarong Lin and Fu Zhang},
year = {2026},
eprint = {2610.25665},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2610.25665},
}
HumanoidPose recovers a humanoid's full-body joint configuration from video alone — useful when onboard state is unavailable, and for turning online robot videos into training data.HumanoidPose 仅凭视频恢复人形机器人的全身关节构型：适用于拿不到机载状态的场景，也能把网上的机器人视频变成训练数据。
@misc{jiang2026vision,
title = {{Vision as Proprioception: Estimating Humanoid Robot Pose from Video}},
author = {Jiaxi Jiang and Matthias Heyrman and René Zurbrügg and Marco Hutter and Christian Holz},
year = {2026},
eprint = {2610.25288},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2610.25288},
}
Measured numbers for robot builders: nine monocular and stereo depth families (Depth Anything V2/3, Depth Pro, MoGe-2, Fast-FoundationStereo, ...) run on a Jetson AGX Orin, scored for metric accuracy and speed.给机器人开发者的实测数据：在 Jetson AGX Orin 上用 TensorRT 运行九类单目与双目深度估计模型（Depth Anything V2/3、Depth Pro、MoGe-2、Fast-FoundationStereo 等），并评测度量精度与速度。
Fine-tunes Qwen3.5-9B on ~1.5M grounding samples auto-built from robot recordings plus other visual data; reports a 75.41 average over seven grounding benchmarks vs 73.68 for GPT-6 Astra.用自动标注的机器人操作录像加多来源视觉数据构建约 150 万条可验证的定位监督，微调 Qwen3.5-9B；报告在七个公开视觉定位基准上平均 75.41 分，GPT-6 Astra 为 73.68。
@misc{wang2026ace,
title = {{ACE-Brain-0.6: Scaling Spatial Grounding for Physical Foundation Models}},
author = {Yinhe Wang and Tao Tao and Zexin He and Shuang Luo and Wei Mao and Yao Mu and Feng Pan and Hanming Deng and Lewei Lu and Zhi Hou and Xingang Pan and Dahua Lin and Dacheng Tao and Xiaogang Wang},
year = {2026},
eprint = {2610.27040},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2610.27040},
}
MIT-licensed visual-inertial odometry for research and products. Supports pinhole and fisheye cameras plus stitched 360° images, with benchmarks against other open-source VIO systems on public datasets.MIT 许可的开源视觉惯性里程计，面向科研与实际应用。支持针孔、鱼眼相机及拼接 360° 图像，并在公开数据集上与其他开源 VIO 系统做了对比。
CoRL 2026 Spotlight. Current-centric streaming 3D reconstruction that predicts window-relative poses and local geometry in the current frame, to limit drift on long runs.CoRL 2026 Spotlight。以当前帧为中心的流式三维重建：在当前帧坐标系预测窗口相对位姿与局部几何，以抑制长时漂移。
@misc{tao2026anchor,
title = {{Anchor3R: Streaming 3D Reconstruction with Transient Anchors for Long-Horizon Visual Mapping}},
author = {Peilin Tao and Chong Cheng and Yuansen Du and Caiwei Song and Zhengqing Chen and Xiaoyang Guo and Wei Yin and Weiqiang Ren and Qian Zhang and Hainan Cui and Shuhan Shen},
year = {2026},
eprint = {2606.05035},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2606.05035},
}
Calibrates wrist and fixed cameras together with no target, from RGB, kinematics and a 3D foundation model; reports 86.4% lower translation and 71.6% lower rotation error in simulation than reconstruction baselines.无需标定板，用 RGB、正运动学和三维基础模型同时标定腕部与固定相机；仿真中平移和旋转误差比基于重建的基线分别降低 86.4% 和 71.6%，并在真机上验证。
@misc{hwang2026anchorhec,
title = {{AnchorHEC: Targetless Hand-Eye Calibration of Wrist and Fixed Cameras}},
author = {Guebin Hwang and Taeyeop Lee and Yeonseo Lee and Hyosup Shin and Sungho Jo},
year = {2026},
eprint = {2611.02884},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.02884},
}
Neural inertial odometry across carriers: a router composes carrier-specific experts, and a light residual branch adapts to new ones. Reports 40% lower ATE than learned baselines.面向多种载体的神经惯性里程计：路由器组合各载体专家，新载体通过轻量残差分支适配。报告 ATE 比学习型基线降低 40%。
@misc{zou2026mosaicimu,
title = {{MosaicIMU: Composing Carrier Experts for Generalizable Neural Inertial Odometry}},
author = {Junye Zou and Huiyi Yan and Xinning Xu and Xiaolei Li and Pengkun Zhou and Jinhui Zhang and Ziyang Meng},
year = {2026},
eprint = {2606.09355},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2606.09355},
}
MoMa-SG builds 3D scene graphs that encode how objects articulate, from RGB-D sequences, and adds the Arti4D-Semantic dataset; demonstrated on a quadruped and a mobile manipulator.MoMa-SG 从 RGB-D 序列构建包含物体铰接方式的 3D 场景图，并发布 Arti4D-Semantic 数据集；在四足和移动操作机器人上演示。
@misc{buchner2026articulated,
title = {{Articulated 3D Scene Graphs for Open-World Mobile Manipulation}},
author = {Martin Büchner and Adrian Röfer and Tim Engelbracht and Tim Welschehold and Zuria Bauer and Hermann Blum and Marc Pollefeys and Abhinav Valada},
year = {2026},
eprint = {2602.16356},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2602.16356},
}
Feature matcher that refines correspondences recurrently in continuous coordinates instead of on fixed grids; reports higher accuracy than Efficient LoFTR at over 10x its speed on embedded hardware.在连续坐标中循环细化对应点、不再依赖固定网格的特征匹配方法；报告精度高于 Efficient LoFTR，在嵌入式硬件上速度超过其 10 倍。
@misc{wang2026corematch,
title = {{CoReMatch: Recurrent Continuous Coordinate Refinement for Real-Time Robotic Feature Matching}},
author = {Robert J. Wang and Charles Ling and Boyu Wang},
year = {2026},
eprint = {2611.03932},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.03932},
}
SLAM that keeps a functional scene graph (which handle opens which drawer) as online state, and uses that topology to help loop closure in repetitive scenes. Reported faster than offline methods at similar accuracy.把功能场景图（如哪个把手开哪个抽屉）作为 SLAM 的在线状态持续维护，并利用其拓扑辅助重复场景的回环检测。报告比离线方法更快且精度相当。
@misc{hu2026functional,
title = {{Functional-SLAM: Interaction-Aware Mapping with Online Functional Scene Graphs}},
author = {Xinggang Hu and Chenyangguang Zhang and Zihan Zhu and Ruida Zhang and Xiangkui Zhang and Xiangyang Ji},
year = {2026},
eprint = {2609.07497},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2609.07497},
}
Turns sparse LiDAR intensity into RGB-like video so camera models work in the dark. Reports better segmentation and lane detection than LiDAR baselines and real cameras across lighting.把稀疏 LiDAR 强度转换为类 RGB 视频，让相机模型在黑暗中也能用。报告在不同光照下，分割与车道线检测优于 LiDAR 基线和真实相机。
@misc{gao2026cyclops,
title = {{Cyclops: LiDAR as a Camera That Dreams in Color}},
author = {Wei Gao and Jian Shu and Mingle Zhao and Maani Ghaffari and David Kong and Chengzhong Xu and Hui Kong},
year = {2026},
eprint = {2608.16264},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2608.16264},
}
Makes dense VLM features spatially consistent by rebuilding each patch from language-labelled visual prototypes; improves open-vocabulary retrieval and 3D mapping. Also ships a compact 25M dense VLM for robots.通过由带语言描述的视觉原型重建每个图像块，让稠密 VLM 特征在空间上更一致，提升开放词汇检索与三维建图；并提供 25M 参数的小型稠密 VLM。
@misc{schwaiger2026resireg,
title = {{ReSiReg: Towards Spatially Consistent Semantics in Language-Conditioned Robotic Tasks}},
author = {Simon Schwaiger and David Seyser and Alessandro Scherl and Wilfried Wöber and Gerald Steinbauer-Wagner},
year = {2026},
eprint = {2606.19088},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2606.19088},
}
Localizes an RGB camera on a floorplan online, querying the map directly and refining poses with diffusion instead of building an offline database. Reports SOTA single-frame and sequential results in real time.直接在平面图上在线定位 RGB 相机：实时查询地图并用扩散模型精化位姿，无需离线数据库。报告单帧与序列定位均达最优且实时运行。
@misc{peng2026freeloc,
title = {{FreeLoc: Online Floorplan Localization via Diffusion-Aided Pose Refinement}},
author = {Haocheng Peng and Boyang Zhou and Jiarui Hu and Xiyue Guo and Ziyang Zhang and Boming Zhao and Yifan Gao and Xiao Li and Hujun Bao and Zhaopeng Cui},
year = {2026},
eprint = {2610.05011},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2610.05011},
}
Maps observations into a latent space organised by affordances (e.g. 'movable') rather than appearance, and adds new affordances when uncertain. Reports 94% inference accuracy, 15+ points above prior work.把视觉观测映射到按功能（如“可移动”）而非外观组织的潜在空间，并在不确定时自动发现新的可供性。报告推断准确率 94%，比已有方法高 15 个百分点以上。
@misc{siva2026what,
title = {{What Objects Enable, Not What They Are: Functional Latent Spaces for Affordance Reasoning}},
author = {Rohan Siva and Neel P. Bhatt and Yunhao Yang and Seoyoung Lee and Nishant Gadde and Christian Ellis and Alvaro Velasquez and Zhangyang Wang and Ufuk Topcu},
year = {2026},
eprint = {2606.05533},
archivePrefix = {arXiv},
primaryClass = {cs.LG},
url = {https://arxiv.org/abs/2606.05533},
}
30M-parameter monocular depth model for transparent and reflective scenes, trained to undo depth-sensor bias with a small rendered set. Reports beating 300M-scale and multi-view models on transparent benchmarks.面向透明与反光场景的 3000 万参数单目深度模型，用少量渲染数据纠正真实深度传感器带来的监督偏差。报告在透明场景基准上超过 3 亿参数级和多视图模型。
@misc{liu2026optigeo,
title = {{OptiGeo: Efficient Monocular Geometry for Embodied Perception in Optically Challenging Scenes}},
author = {Muxin Liu and Tianbo Liu and Jing Xia and Xiaoyang Lyu and Xiaoshan Wu and Bo Wang and Peng Dai and Zhongrui Wang and Shaoshuai Shi and Xiaojuan Qi},
year = {2026},
eprint = {2608.29881},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2608.29881},
}
Treats spoken descriptions ('my bag is on the table') as sensor readings: a model outputs a calibrated spatial distribution that is fused with onboard perception in one belief map. VLA-3D benchmark + real robot.把自然语言描述（如“包在桌上”）当作传感器观测：模型输出校准过的空间概率分布，并与机载感知融合到统一的信念地图中。在 VLA-3D 基准和真机上验证。
@misc{naveen2026language,
title = {{Language as a Sensor: Calibrated Spatial Belief Estimation in 3D Scenes from Natural Language}},
author = {Aryan Naveen and Jason Xinyu Liu and Luca Carlone and Andreea Bobu},
year = {2026},
eprint = {2606.08666},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2606.08666},
}
Active in-hand 3D reconstruction: estimates per-ray reconstruction uncertainty to pick the next view, then an in-hand rotation policy turns the object to expose it. Better quality and efficiency than non-active rotation.主动式手内三维重建：沿候选视线估计各方向的重建不确定性来选择下一最佳视角，再由手内旋转策略把物体转到该视角。重建质量与效率均优于非主动旋转。
FAH builds on SAM 3D Body's hand branch: predict 2D/3D joints and surface points, then fit MANO or MHR-Hand, with optional contact and world-space tracking. The default ViT-L runs at 65 fps on an RTX 4070 Ti SUPER.FAH 基于 SAM 3D Body 的手部分支：先预测 2D/3D 关节与表面点，再拟合 MANO 或 MHR-Hand，可选估计接触并在世界坐标系中跟踪。默认 ViT-L 模型在 RTX 4070 Ti SUPER 上达 65 fps。
@misc{cao2026fast,
title = {{Fast and Accurate Hand Estimation in Pixels, Interaction and World Space}},
author = {Jinkun Cao},
year = {2026},
eprint = {2611.07711},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2611.07711},
}
Relative 6-DoF pose between two image groups (relocalization, multi-camera rigs): keeps a multi-view foundation model frozen and adds ~32M trainable parameters (resampler, cross-group bridge, pose head).估计两组图像之间的相对 6 自由度位姿（跨序列重定位、多相机里程计）：保持多视图基础模型冻结，只增加约 3200 万可训练参数（重采样器、跨组桥接模块、多帧位姿头）。
@misc{wei2026g,
title = {{G2G: Exploiting Intra-Group Geometry for Inter-Group Pose Estimation}},
author = {Yufei Wei and Shuhao Ye and Chenxiao Hu and Yiyuan Pan and Dongyu Feng and Rong Xiong and Yue Wang and Yanmei Jiao},
year = {2026},
eprint = {2606.08284},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2606.08284},
}
DeepCORD unrolls a parallel accelerated Riemannian optimizer and learns a self-supervised policy that tunes solver parameters by phase and communication status. Tested on SE(3) pose graphs and SL(4).DeepCORD 把并行加速的黎曼优化器展开为可微迭代，并自监督学习一个依据优化阶段与通信状态调节求解参数的策略。在真实 SE(3) 位姿图与 SL(4) 子图对齐上测试。
Neural inertial odometry whose mean and covariance transform correctly under any IMU mounting rotation; Last-Frame Alignment makes sensor-frame training match world-frame. TLIO ATE: 2.018 m vs 76.389 m for EqNIO.神经惯性里程计：输出的均值与协方差在任意 IMU 安装旋转下都按张量规律变换；Last-Frame Alignment 使传感器坐标系训练等价于世界坐标系训练。在 TLIO 上 ATE 为 2.018 米，EqNIO 为 76.389 米。
@misc{kim2026ginio,
title = {{GINIO: A Geometric SO(3)-Equivariant Interface for Neural Inertial Odometry}},
author = {Chankyo Kim and Minghan Zhu and Tzu-Yuan Lin and Avantika Rattan and Maani Ghaffari},
year = {2026},
eprint = {2609.25338},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2609.25338},
}
Treats camera motion as an action: given an image and a language intent ('look behind the box'), predict the next relative camera pose. Supervision is mined from egocentric video by hindsight labeling.把相机运动当作一种动作：给定当前图像和语言意图（如“看看箱子后面”），预测下一视角的相对相机位姿。监督信号通过事后标注从第一人称视频中挖掘。
@misc{sun2026lime,
title = {{LIME: Learning Intent-aware Camera Motion from Egocentric Video}},
author = {Boyang Sun and Jiajie Li and Yung-Hsu Yang and Chenyangguang Zhang and Tim Engelbracht and Sunghwan Hong and Cesar Cadena and Marc Pollefeys and Hermann Blum},
year = {2026},
eprint = {2607.02417},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2607.02417},
}
Restructures deep feature matchers so cross-image interaction happens only in the last layers; per-image context blocks are cached offline. Reports over 2x lower compute, plus 10-14% from entropy-guided token reduction.重构深度特征匹配器，把跨图像交互推迟到最后几层，单图上下文模块可离线缓存。报告计算量降低一半以上，熵引导的 token 裁剪再省 10–14%。
Online 3DGS mapping that integrates each Gaussian over the exposure time analytically to handle motion blur, and prunes by a Hessian score. Matches offline deblurring 3DGS at 15-150x the speed.在线 3DGS 建图：对每个高斯在曝光时间内解析积分以处理运动模糊，并用 Hessian 得分剪枝控制数量。渲染质量与离线去模糊 3DGS 相当，速度快 15–150 倍。
@misc{jung2026romo,
title = {{RoMo-GS: Efficient Online 3D Gaussian Splatting for Robot Mapping via Exposure-Integrated Motion Blur}},
author = {Sangwoo Jung and Di Deng and Jiahui Fu and Laura Herlant and Ayoung Kim and Yafei Hu},
year = {2026},
eprint = {2610.24605},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2610.24605},
}
Open-vocabulary 3D affordance detection: MLLM output tokens pull multi-scale geometry from a frozen 3D VQ-VAE through gated cross-attention before mask decoding. Reports about +8% mIoU.开放词汇 3D 可供性检测：多模态大模型的输出 token 在解码掩码前，通过门控交叉注意力从冻结的 3D VQ-VAE 中检索多尺度几何特征。报告 mIoU 提升约 8%。
@misc{sun2026voxafford,
title = {{VoxAfford: Multi-Scale Voxel-Token Fusion for Open-Vocabulary 3D Affordance Detection}},
author = {Haowen Sun and Shaolong Zhang and Mingyang Li and Chengzhong Ma and Xinzhe Chen and Qiongjie Cui and Xingyu Chen and Zeyang Liu and Xuguang Lan},
year = {2026},
eprint = {2605.01365},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2605.01365},
}
Aligns two RGB-only egocentric captures of a room taken at different times: builds object-level 3D scene graphs with foundation models and lets a VLM match objects across them. No training or depth sensor.对齐同一房间在不同时间的两段纯 RGB 第一人称录像：用基础模型构建物体级 3D 场景图，再让 VLM 跨两段录像匹配物体实例。无需训练或深度传感器。
@misc{chen2026prose,
title = {{PROSE: Training-Free Egocentric Scene Registration with Vision-Language Models}},
author = {Zhiang Chen and Nahyuk Lee and Boyang Sun and Taein Kwon and Marc Pollefeys and Zuria Bauer and Sunghwan Hong},
year = {2026},
eprint = {2606.16569},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2606.16569},
}
@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},
}
Benchmark of 22.5K verified egocentric interactions with pixel-precise contact points: current models often miss where to touch. As a memory bank for an affordance policy it lifts real grasp success from 16% to 58%.第一视角接触点预测基准：2.25 万个人工核验的交互事件，每个含接触前画面、语义意图与像素级接触位置。现有方法常常定位不准甚至找不到目标物体；把 EgoContact 用作已有可供性迁移策略的记忆库，真机抓取成功率从 16% 提升到 58%。
@misc{deryo2026egocontact,
title = {{EgoContact: Evaluating Physical Intelligence with Egocentric Video}},
author = {Adam Deryło and Alexey Gavryushin and Daniel Cremers and Marc Pollefeys and Xi Wang},
year = {2026},
eprint = {2610.39167},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2610.39167},
}
Learns one static-and-dynamic representation across different visuo-tactile sensors, and contributes TacQuad, an aligned multi-sensor tactile dataset.跨多种视触觉传感器学习统一的静态-动态表征，并贡献对齐的多传感器触觉数据集 TacQuad。
@misc{feng2025anytouch,
title = {{AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors}},
author = {Ruoxuan Feng and Jiangyu Hu and Wenke Xia and Tianci Gao and Ao Shen and Yuhao Sun and Bin Fang and Di Hu},
year = {2025},
eprint = {2502.12191},
archivePrefix = {arXiv},
primaryClass = {cs.LG},
url = {https://arxiv.org/abs/2502.12191},
}
@misc{zhou2025roborefer,
title = {{RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics}},
author = {Enshen Zhou and Jingkun An and Cheng Chi and Yi Han and Shanyu Rong and Chi Zhang and Pengwei Wang and Zhongyuan Wang and Tiejun Huang and Lu Sheng and Shanghang Zhang},
year = {2025},
eprint = {2506.04308},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2506.04308},
}
RoboTracer is a 3D-aware VLM for spatial tracing, which needs multi-step metric reasoning about real-world measurements.RoboTracer 是三维感知 VLM，用于空间轨迹推理，需要结合真实度量做多步推理。
@misc{zhou2025towards,
title = {{Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics}},
author = {Enshen Zhou and Yibo Li and Jingkun An and Jiayuan Zhang and Shanyu Rong and Mengzhen Liu and Yi Han and Yuheng Ji and Huajie Tan and Jiawei He and Pengwei Wang and Zhongyuan Wang and Cheng Chi and Lu Sheng and Shanghang Zhang},
year = {2025},
eprint = {2512.13660},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2512.13660},
}
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。
@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},
}
TaRF puts vision and touch in one 3D space: touch probes are registered to photos, and a conditional diffusion model estimates touch at unprobed positions.TaRF 把视觉与触觉放进同一三维空间：将触摸采样配准到照片，并用条件扩散模型估计未采样位置的触觉。
@misc{dou2024tactile,
title = {{Tactile-Augmented Radiance Fields}},
author = {Yiming Dou and Fengyu Yang and Yi Liu and Antonio Loquercio and Andrew Owens},
year = {2024},
eprint = {2405.04534},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2405.04534},
}
SpatialBot feeds RGB and depth into a VLM for better spatial understanding, with the SpatialQA dataset.SpatialBot 向 VLM 同时输入 RGB 和深度以提升空间理解，并提供 SpatialQA 数据集。
@misc{cai2024spatialbot,
title = {{SpatialBot: Precise Spatial Understanding with Vision Language Models}},
author = {Wenxiao Cai and Iaroslav Ponomarenko and Jianhao Yuan and Xiaoqi Li and Wankou Yang and Hao Dong and Bo Zhao},
year = {2024},
eprint = {2406.13642},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2406.13642},
}
NeuralFeels fuses vision and touch from a multi-fingered hand into an online neural field, reconstructing an object's shape and tracking its pose while the hand manipulates it.NeuralFeels 将多指手的视觉与触觉在线融合为神经场，在操作过程中同时重建物体形状并跟踪其位姿。
@misc{suresh2023neural,
title = {{Neural feels with neural fields: Visuo-tactile perception for in-hand manipulation}},
author = {Sudharshan Suresh and Haozhi Qi and Tingfan Wu and Taosha Fan and Luis Pineda and Mike Lambeta and Jitendra Malik and Mrinal Kalakrishnan and Roberto Calandra and Michael Kaess and Joseph Ortiz and Mustafa Mukadam},
year = {2023},
eprint = {2312.13469},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2312.13469},
}
Builds an object-level 3D scene graph labelled by vision-language models, which an LLM planner can query in natural language.用视觉语言模型构建带语义标注的物体级三维场景图，大模型规划器可以用自然语言查询。
@misc{gu2023conceptgraphs,
title = {{ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning}},
author = {Qiao Gu and Alihusein Kuwajerwala and Sacha Morin and Krishna Murthy Jatavallabhula and Bipasha Sen and Aditya Agarwal and Corban Rivera and William Paul and Kirsty Ellis and Rama Chellappa and Chuang Gan and Celso Miguel de Melo and Joshua B. Tenenbaum and Antonio Torralba and Florian Shkurti and Liam Paull},
year = {2023},
eprint = {2309.16650},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2309.16650},
}
CLIP-Fields learns a mapping from 3D points to semantic embeddings using only weak supervision, giving robots a searchable spatial memory.CLIP-Fields 仅用弱监督学习三维点到语义嵌入的映射，为机器人提供可检索的空间记忆。
@misc{shafiullah2022clip,
title = {{CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory}},
author = {Nur Muhammad Mahi Shafiullah and Chris Paxton and Lerrel Pinto and Soumith Chintala and Arthur Szlam},
year = {2022},
eprint = {2210.05663},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2210.05663},
}
2.4M egocentric RGB-D frames (4,000+ sequences, 800 object instances in 16 categories, 610 rooms) of people handling rigid and articulated objects, with segmentation, hand and object pose labels.240 万帧第一视角 RGB-D（4000 多段序列、16 类 800 个物体实例、610 个房间），记录人操作刚体与铰接物体，带分割、手部与物体位姿标注。
@misc{liu2022hoi,
title = {{HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction}},
author = {Yunze Liu and Yun Liu and Che Jiang and Kangbo Lyu and Weikang Wan and Hao Shen and Boqiang Liang and Zhoujie Fu and He Wang and Li Yi},
year = {2022},
eprint = {2203.01577},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2203.01577},
}
2.1M video frames of two hands manipulating articulated objects (scissors, laptops…) with accurate 3D hand and object meshes from motion capture; a reference for bimanual hand-object reconstruction.210 万帧双手操作铰接物体（剪刀、笔记本电脑等）的视频，借助动作捕捉提供精确的手与物体三维网格；双手-物体重建的常用基准。
@misc{fan2022arctic,
title = {{ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation}},
author = {Zicong Fan and Omid Taheri and Dimitrios Tzionas and Muhammed Kocabas and Manuel Kaufmann and Michael J. Black and Otmar Hilliges},
year = {2022},
eprint = {2204.13662},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2204.13662},
}
Contact-GraspNet — predicts 6-DoF parallel-jaw grasps for a whole cluttered scene from one depth view by treating observed points as grasp contacts, which shrinks the problem to 4 DoF per point.Contact-GraspNet：从单帧深度图为整个杂乱场景预测 6 自由度平行夹爪抓取；把观测到的点当作抓取接触点，使每个点只需学习 4 个自由度。
@misc{chao2021dexycb,
title = {{DexYCB: A Benchmark for Capturing Hand Grasping of Objects}},
author = {Yu-Wei Chao and Wei Yang and Yu Xiang and Pavlo Molchanov and Ankur Handa and Jonathan Tremblay and Yashraj S. Narang and Karl Van Wyk and Umar Iqbal and Stan Birchfield and Jan Kautz and Dieter Fox},
year = {2021},
eprint = {2104.04631},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2104.04631},
}
SemExp builds an episodic semantic map and learns a policy that picks long-term goals on it, a modular recipe that became a standard ObjectNav baseline in Habitat.SemExp 构建情景语义地图，并学习在地图上选择长期目标的策略；这一模块化方案成为 Habitat 中 ObjectNav 的常用基线。
Splits exploration into a learned neural SLAM module, a global policy that chooses long-term goals and a local policy that reaches them, which is far more sample-efficient than end-to-end RL.将探索拆为可学习的神经 SLAM 模块、选择长期目标的全局策略和到达目标的局部策略，比端到端强化学习样本效率高得多。
@misc{chaplot2020learning,
title = {{Learning to Explore using Active Neural SLAM}},
author = {Devendra Singh Chaplot and Dhiraj Gandhi and Saurabh Gupta and Abhinav Gupta and Ruslan Salakhutdinov},
year = {2020},
eprint = {2004.05155},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2004.05155},
}
EPIC-KITCHENS-100 — 100 hours (20M frames, ~90K action segments) of unscripted first-person kitchen video from 45 environments, with dense action labels and challenges such as action anticipation.EPIC-KITCHENS-100：来自 45 个厨房环境、100 小时（2000 万帧、约 9 万个动作片段）的非脚本第一视角视频，动作标注密集，并设有动作预测等挑战任务。
@misc{damen2020rescaling,
title = {{Rescaling Egocentric Vision}},
author = {Dima Damen and Hazel Doughty and Giovanni Maria Farinella and Antonino Furnari and Evangelos Kazakos and Jian Ma and Davide Moltisanti and Jonathan Munro and Toby Perrett and Will Price and Michael Wray},
year = {2020},
eprint = {2006.13256},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2006.13256},
}
Abhishek Goudar, Jonathan Kelly, Timothy D. Barfoot
Abstract摘要
Multi-sensor state estimation requires accurate spatial and temporal calibration between heterogeneous sensors. Existing spatiotemporal calibration methods typically represent sensor extrinsic parameters as a rigid-body transformation together with a scalar temporal offset, causing the spatial and temporal parameters to enter the estimation problem through separate mechanisms. While the spatial transformation composes directly with the robot pose, accounting for the temporal offset requires evaluating the trajectory at a shifted time, typically through motion compensation, interpolation, or a …
Maolin Ye, Dongqing Zhao, Linyang Li, Shuai Xue et al.
Abstract摘要
To address unreliable cross-view association in long-sequence feed-forward dense SLAM, this letter presents V3DSAM, an open-vocabulary semantic dense SLAM system that establishes physical correspondences at both the scene and object levels. The system combines feed-forward geometric estimates from VGGT-SLAM 2.0 with open-vocabulary semantic observations from SAM3. We introduce semantic-geometric dual-scale loop verification, which identifies false loop closures using pixel-level bidirectional reprojection and object-level 3D spatial correspondences, without accessing backbone-internal …
@misc{ye2026v,
title = {{V3DSAM: Semantic-Geometric Loop Verification and Geometry-Anchored Persistent Instance Mapping for Feed-Forward Dense SLAM}},
author = {Maolin Ye and Dongqing Zhao and Linyang Li and Shuai Xue and Yuan Liu and Yiyuan Wang and Wen Li},
year = {2026},
eprint = {2611.12452},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.12452},
}
Yifan Luo, Takafumi Matsumaru, Vibekananda Dutta, Xin He
Abstract摘要
This paper presents DPGS-SLAM (Diffusion-Prior and Provenance-Aware Monocular Gaussian Splatting SLAM) for dense mapping in environments containing dynamic objects. Dynamic observations can contaminate camera tracking and scene reconstruction in visual SLAM (simultaneous localization and mapping). Although 3DGS (3D Gaussian splatting) enables efficient dense mapping, existing 3DGS-SLAM systems may exhibit instability when dynamic objects violate their underlying static-scene assumption. Excluding dynamic observations can reduce their influence on tracking and mapping, but may leave occluded …
@misc{luo2026dpgs,
title = {{DPGS-SLAM: Diffusion-Prior and Provenance-Aware Monocular Gaussian Splatting SLAM for Dynamic Visual Sensing}},
author = {Yifan Luo and Takafumi Matsumaru and Vibekananda Dutta and Xin He},
year = {2026},
eprint = {2611.12038},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.12038},
}
Mingyang Yang, Zeyu Sha, Xiaorui Wang, Jun Wang et al.
Abstract摘要
Underwater leader-follower formation control requires continuous relative-pose estimation despite degraded sensing conditions and limited onboard computation. This paper presents a reliability-adaptive multimodal perception framework for six-degree-of-freedom relative-pose tracking between two moving underwater robots. The framework integrates complementary visual, acoustic-ranging, and hydrodynamic measurements while accounting for their distinct physical characteristics and time-varying reliability. It adaptively weights modality contributions and models temporal dependencies with linear …
@misc{yang2026reliability,
title = {{Reliability-Adaptive Multimodal Relative Pose Tracking for Underwater Leader-Follower Robots}},
author = {Mingyang Yang and Zeyu Sha and Xiaorui Wang and Jun Wang and David Chen Wang and Feitian Zhang},
year = {2026},
eprint = {2611.11940},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.11940},
}
Wanhui Luo, Hongbo Zhao, Yi Zhou, Qijun Chen et al.
Abstract摘要
The wide field of view of fisheye cameras and the simplicity of a monocular setup make monocular fisheye visual odometry (VO) attractive for robotic localization and mapping. Nevertheless, scale drift remains a major challenge over long trajectories. Unsupervised depth learning can help to mitigate this issue, but the pronounced distortion of fisheye images poses challenges for accurate depth estimation. This article presents S$^2$D-FVO, a monocular fisheye VO framework integrating spherical bundle adjustment (SBA)-guided unsupervised depth learning to improve scale consistency and depth …
@misc{luo2026scale,
title = {{Scale-Consistent Monocular Fisheye Visual Odometry via Spherical Bundle Adjustment-Guided Unsupervised Depth Learning}},
author = {Wanhui Luo and Hongbo Zhao and Yi Zhou and Qijun Chen and Yiming Nie and Rui Fan},
year = {2026},
eprint = {2611.11934},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2611.11934},
}
Khanh Nguyen, Thomas Walker, Hichem Telli, Carlos de la Torre-Ortiz et al.
Abstract摘要
High-fidelity LiDAR simulation remains a bottleneck for scalable development and validation of autonomous systems. Existing generators can synthesize realistic scans, but they are typically constrained to a single sensor configuration, offer limited control over structure and geometry, and drift in long-horizon 4D generation. We present CrossLiDAR, a unified transformer-based framework capable of generating controllable and spatio-temporally consistent multi-sensor LiDAR sequences. Our approach leverages a rectified flow objective with a Multi-Modal Diffusion Transformer (MM-DiT) backbone, …
@misc{nguyen2026crosslidar,
title = {{CrossLiDAR: Controllable Multi-Sensor LiDAR Sequence Generation}},
author = {Khanh Nguyen and Thomas Walker and Hichem Telli and Carlos de la Torre-Ortiz and Stefano Fiorini and Salah Eddine Bekhouche and Mohammed-En-Nadhir Zighem and Wassim Swaileh and others},
year = {2026},
eprint = {2611.11131},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2611.11131},
}
Krishnan Harikumar, Alejandro Fontan, Thierry Peynot, Emili Hernández et al.
Abstract摘要
While 3D Gaussian Splatting (3DGS) is typically optimized from images only, many robotics and mapping applications provide both camera and high-definition LiDAR data, combining rich visual appearance with accurate geometric structure. We introduce PLS-GS, a probabilistic LiDAR scaffold for Gaussian Splatting that exploits this complementary sensing setting to construct a compact 3DGS representation aligned to the measured surface. PLS-GS fits a Hierarchical Gaussian Mixture Model jointly over position and color, yielding a continuous and adaptive scaffold that eliminates the need for discrete …
Mingqiao Han, Qigeng Duan, Xuchen Liu, Jinqiang Cui et al.
Abstract摘要
LiDAR-based localization and mapping systems produce registered point clouds that serve as geometric measurements for downstream estimation and navigation. Registration errors introduce duplicated surfaces and structural deformation into these measurements. In the absence of an independent reference, online assessment relies on geometry accumulated from earlier measurements. Such assessment requires tolerance to sampling variation and an accumulation process in which observations enter the history only after evaluation. We therefore formulate a recursive Bayesian comparison that couples …
@misc{han2026online,
title = {{Online Geometric Consistency Assessment of LiDAR Measurements via Recursive Bayesian Comparison}},
author = {Mingqiao Han and Qigeng Duan and Xuchen Liu and Jinqiang Cui and Xi Chen and Ben M. Chen},
year = {2026},
eprint = {2611.10566},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.10566},
}
Kaiyao Liao, Qingfeng Li, Chen Chen, Qing Sun et al.
Abstract摘要
In real homes, assistive robots must repeatedly locate targets from large furniture to tiny tabletop items, as people move objects between household surfaces. Uniformly instantiating detections at different scales as 3D objects can be brittle for small on-surface items; without explicit object-state validation, stale entries may persist after scene changes. Our key insight is to separate persistent 3D furniture entities from revisable surface-object hypotheses, retaining their visual evidence without requiring independent object geometry. We formalize this design as the Hypothesis Scene Graph …
@misc{liao2026hsgnav,
title = {{HSGNav: Hypothesis Scene Graphs for Multi-Scale Lifelong Navigation under Object Relocation}},
author = {Kaiyao Liao and Qingfeng Li and Chen Chen and Qing Sun and Ningbo Gu and Xiaoze Wu and Haochen Zhao and Ying Li and others},
year = {2026},
eprint = {2611.10547},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.10547},
}
Quanyun Wu, Kyle Gao, Daisy Li, Kshitij Goyal et al.
Abstract摘要
Feed-forward 3D reconstruction turns an uncalibrated monocular stream into a dense point cloud in a single inference pass, orders of magnitude faster than classical structure-from-motion (e.g., COLMAP), and reliable on the weakly textured, repetitive surfaces where keypoint matching fails outright. However, raw point clouds lack the object identity, physical properties, and watertight volume required for robot learning. This gap widens under robot-native capture. A camera mounted on a robot constrained to a few degrees of freedom sees each object only partially, and the repetitive, weakly …
@misc{wu2026officetwin,
title = {{OfficeTwin: Realizing 3D Reconstruction of Redundant Scenes through Partial Viewpoint Perception}},
author = {Quanyun Wu and Kyle Gao and Daisy Li and Kshitij Goyal and Dayou Mao and David A. Clausi and Jonathan Li and Yuhao Chen},
year = {2026},
eprint = {2611.10241},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.10241},
}
Geometric foundation models estimate dense geometry and camera parameters from monocular images, but reliable SLAM also requires consistent scale and accurate data association across successive reconstructions. We present DASH-SLAM, a monocular SLAM system that integrates metric depth predictions from pretrained Depth Anything 3 into a shared-keyframe pose graph without task-specific fine-tuning. DASH-SLAM derives scale corrections from depth ratios at shared anchor images and accumulates them across reconstructions, with a damping factor controlling their influence. These corrections rescale …
Inertial odometry is a compelling approach to state estimation for agile quadrotor flight due to its affordability, low weight, and robustness to perceptual degradation. However, relying only on integrated inertial measurements is impractical, as sensor errors and time-varying biases lead to significant pose drift. Although recent advances have enabled inertial odometry for drone racing, existing approaches show limited generalization to trajectories not seen during training. This work improves generalization by adopting a body-frame representation and incorporating body-frame torque dynamics …
Duc Manh Do, Thanh Nguyen Canh, Ngoc Minh Do, Mai Thanh Thai et al.
Abstract摘要
Autonomous 3D exploration with UAVs requires efficient target selection under limited flight time and onboard computation. In conventional Euclidean-distance-based frontier pipelines, geometric distance may poorly represent the actual collision-free travel cost in cluttered environments, leading to inefficient frontier choices. This paper presents a lightweight path-aware frontier re-ranking method for LiDAR-based UAV exploration. The method first retains a small top-N set of promising frontier candidates using a lightweight utility function and then applies time-bounded RRT* planning to …
@misc{do2026lightweight,
title = {{Lightweight Path-Aware Frontier Re-ranking for LiDAR-Based UAV Exploration}},
author = {Duc Manh Do and Thanh Nguyen Canh and Ngoc Minh Do and Mai Thanh Thai and Xiem HoangVan},
year = {2026},
eprint = {2611.09561},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.09561},
}
Yujie Zhang, Yuxuan Guo, Xinbao Sun, Chunlei Zhao et al.
Abstract摘要
Building information models (BIM) can provide a global geometric reference for robot localization with LiDAR-inertial odometry (LIO). However, as-built deviations from the as-designed model mean that a disagreement between a scan and the BIM may arise from a pose error, an offset wall surface (an as-built deviation or an unmodeled object in front of the wall), or a shifted room, and in some geometries these explanations produce identical observations. In this paper, we formalize this attribution problem as fault identification over three fault classes and derive a geometric criterion for when …
@misc{zhang2026when,
title = {{When to Trust the BIM: Identifiability-Aware LiDAR-Inertial--BIM Fusion under As-Built Deviations}},
author = {Yujie Zhang and Yuxuan Guo and Xinbao Sun and Chunlei Zhao and Langqi Miao and Xiaohui Jia and Jinyue Liu},
year = {2026},
eprint = {2611.09045},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.09045},
}
Human videos contain abundant object-manipulation demonstrations, but they do not directly provide motion cues that a robot can follow. We present HOC2R, a Hand-Object Contact trajectory extractor for Robot motion that combines frozen DINOv3 and SAM 2.1 features with learned heads for hand-object association and contact localization. HOC2R supports two modes: count-aware automation that detects, counts, and localizes visible contacts in untrimmed videos, and fixed-two localization for two-finger grippers when contact frames are known. On a 30-task point-annotated benchmark, count-aware …
@misc{yu2026hoc,
title = {{HOC2R: Hand-Object Contact Trajectories for Human-to-Robot Motion Transfer}},
author = {Hongkun Yu and Francisco M. López and Francisco Cruz},
year = {2026},
eprint = {2611.08920},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.08920},
}
Shuntian Zheng, Guangming Wang, Hongyang He, Shuai He et al.
Abstract摘要
Assistive robots and search-and-rescue platforms require reliable human state sensing in smoke, darkness, and privacy-sensitive environments, where cameras and LiDAR may be unreliable Millimeter-wave radar offers an alternative that works without ambient light, penetrates smoke, and does not capture visual appearance. However, the compact arrays that fit robot size, power, and cost budgets have limited apertures, producing joint-localization errors on the order of decimeters at a few meters, large enough to compromise the safety margins and tracking accuracy a robot depends on. Existing …
@misc{zheng2026what,
title = {{What Limits mmWave Human-State Sensing for Robot Perception?}},
author = {Shuntian Zheng and Guangming Wang and Hongyang He and Shuai He and Yu Guan},
year = {2026},
eprint = {2611.08863},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.08863},
}
Aditya Iyer, Andy Ye, Akshay Narayan, Nora Ayanian
Abstract摘要
Cooperative localization uses odometry and inter-robot measurements to estimate the motion of a robot team. These measurements describe only relative geometry, but the team's estimated position and orientation can drift together over time, i.e., gauge drift. In this work, we study correction of this gauge drift using a radio attenuation map registered in the same world coordinate frame used for robot poses. Specifically, we propose Radio-to-Pose Information (RPI), an interface that converts power residuals and their pose derivatives into a Gaussian information matrix and vector pair. RPI …
@misc{iyer2026radio,
title = {{Radio-to-Pose Information for Gauge-Drift Correction in Cooperative Localization}},
author = {Aditya Iyer and Andy Ye and Akshay Narayan and Nora Ayanian},
year = {2026},
eprint = {2611.08361},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.08361},
}
Iaroslav Kolomiets, Iaroslav Sheipak, Mikhail Reppo, Vsevolod Egorov et al.
Abstract摘要
Vision-based rover autonomy requires integrating perception, localization, planning and platform-specific control under limited sensing and computing resources. We present an open-source ROS 2 stack for following directional arrows, reaching a terminal cone and returning autonomously to the start. It connects YOLOv8n detection and geometric direction, range and bearing estimation with RGB-D SLAM, wheel-inertial state estimation, kinematics-aware planning, behavior-tree mission management and STM32 actuation. Standard interfaces separate reusable autonomy from the hardware layer; a …
@misc{kolomiets2026integrated,
title = {{An Integrated Open-Source Stack for Vision-Based Autonomous Navigation of Wheeled Rovers}},
author = {Iaroslav Kolomiets and Iaroslav Sheipak and Mikhail Reppo and Vsevolod Egorov and Viktor Chertopolokhov and Isaac Chairez},
year = {2026},
eprint = {2611.08100},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.08100},
}
Simone D'Angelo, Gianmarco Corrado, Federico Esposito, Vincenzo Scognamiglio et al.
Abstract摘要
Visual-inertial odometry (VIO) can degrade during aerial inspection in repetitive or poorly textured environments. We propose an active environment-modification framework for unmanned aerial vehicles (UAVs) relying on cameras and an inertial measurement unit only, without prior maps or additional localization sensors. Inspired by the fairy tale of Tom Thumb, the UAV creates visual features on demand by releasing ground markers or marking walls through physical contact. An information-based indicator triggers interventions using temporal confirmation and hysteresis. Evaluation includes three …
Junkai Niu, Sheng Zhong, Delei Kong, Xin Wang et al.
Abstract摘要
Event cameras are neuromorphic vision sensors with pixels that independently and asynchronously respond to brightness changes at microsecond resolution, supporting state estimation under rapid motion, motion blur, and high dynamic range (HDR) illumination. This also enables capture of high-frequency blinking patterns from light-emitting diodes (LEDs). Based on this, we propose a real-time event-based framework for LED tracking and six-degree-of-freedom (6-DoF) relative pose estimation using pulse-width modulation (PWM)-encoded LED markers. Multiple LEDs share a common blinking frequency and …
@misc{niu2026real,
title = {{Real-Time Event-Based LED Tracking and Pose Estimation with PWM-Encoded Markers}},
author = {Junkai Niu and Sheng Zhong and Delei Kong and Xin Wang and Kaizhen Sun and Yusen Zhang and Mingzhen Gan and Yi Zhou},
year = {2026},
eprint = {2611.07630},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.07630},
}
Fan Yang, Tatsuya Kikuzuki, Jun Liang, Jun Liu et al.
Abstract摘要
To serve a request in a human environment, a robot system must find an object that satisfies a functional requirement and a robot that can feasibly reach it. Scene graphs record which objects exist and where, but they often omit capabilities documented only in product manuals. Retrieval-augmented generation methods can read such manuals, yet they rarely reason jointly over object capabilities, physical instances, robot states, and dynamic connectivity. We introduce E2W-Bench, the Exists-to-Works Benchmark, which links dynamic hybrid scene graphs with real product manuals to evaluate …
@misc{yang2026embodied,
title = {{Embodied RAG++: Retrieval-Augmented Generation From What Exists to What Works in Embodied Scenes}},
author = {Fan Yang and Tatsuya Kikuzuki and Jun Liang and Jun Liu and Wenkai Li and Ryosuke Kawamura and Ananya Hazarika and Prajit KrisshnaKumar and others},
year = {2026},
eprint = {2611.07517},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.07517},
}
Reon Tabata, Kenji Koide, Shuji Oishi, Taku Okawara et al.
Abstract摘要
LiDAR-Inertial-Visual Odometry (LIVO) integrates complementary LiDAR, camera, and IMU measurements to achieve robust state estimation. However, most existing methods assume a fixed relative pose and accurate time synchronization between sensors. Toward modular and heterogeneous robotic systems, this paper presents FREE-LIVO, a tightly coupled odometry method that requires neither a rigid LiDAR-camera rig nor LiDAR-camera time synchronization. The proposed method uses a pretrained image feature matcher to establish correspondences between a camera image and a dense LiDAR intensity image …
Ground robots operating in temperate forests suffer from systematic LiDAR occlusions caused by tree trunks, creating persistent blind regions that degrade traversability estimation. In this paper, we propose FOSCo-Net, a self-supervised voxel completion framework that learns to reconstruct occluded geometry from a single scan using temporally accumulated observations as automatic supervision, and we evaluate cylindrical and Cartesian ego-centric grids with multiple decoder designs. FOSCo-Net consistently improves reconstruction quality and traversal safety, with a gated skip decoder achieving …
Jingwen Yu, Pengyu Wang, Jin Wu, Weinan Chen et al.
Abstract摘要
Loop closure detection conventionally cascades separate models for global retrieval, geometric verification, and relative pose estimation, leading to redundant computation and disconnected visual representations. We propose UniLoop, a unified framework that reuses the hierarchical representations of the pretrained geometric foundation model throughout this pipeline. A shared image encoder produces features for compact global descriptors; the same features are passed to the cross-view decoder for pairwise verification; and the original geometric predictions provide relative camera constraints …
@misc{yu2026uniloop,
title = {{UniLoop: Unified Loop Closure Detection from Retrieval to Geometric Verification and Relative Pose Estimation}},
author = {Jingwen Yu and Pengyu Wang and Jin Wu and Weinan Chen and Ping Tan and Hong Zhang},
year = {2026},
eprint = {2611.06378},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.06378},
}
Ziyi Jin, Kangjin Yu, Beichen Wang, Can Jiang et al.
Abstract摘要
Feed-forward geometric foundation models enable dense monocular reconstruction without requiring camera calibration, but independently reconstructed submaps can accumulate scale drift, and even a valid revisit can yield an inconsistent cross-submap measurement. We extend VGGT-SLAM 2.0 with fixed-root scale anchoring and short-sequence-assisted direct loop connections. SALAD selects an image pair between the initial submap and each eligible new submap; joint VGGT inference then uses learned implicit semantic-geometric cues to supply a scale-only anchor while preserving the original overlap …
@misc{jin2026scale,
title = {{Scale Anchoring via Implicit Semantics and Sequence-Consistent Loop Closure for VGGT-Based SLAM}},
author = {Ziyi Jin and Kangjin Yu and Beichen Wang and Can Jiang and Zhongpu Xia and Jie Xu},
year = {2026},
eprint = {2611.06308},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.06308},
}
Projector-based augmented reality enables natural interaction between users and devices by overlaying digital information onto the physical world through projected imagery. A key technical requirement of such systems is accurate positional alignment between the projector and the devices. Pixel-level Visible Light Communication (PVLC) achieves this alignment without external sensing infrastructure by embedding invisible spatial codes into each projected pixel through high-speed brightness modulation that preserves image quality. However, the information that PVLC transmits is inherently …
Uihyun Hwang, Sungjae Shin, Dongjae Kim, Hyun Myung
Abstract摘要
Visual-inertial odometry relies on visual features that correspond to 3D points with consistent projections across sequential frames. In reflective indoor-floor environments, however, specular floor patterns can be detected and triangulated as virtual features below the physical ground plane, producing unreliable feature associations and inconsistent visual residuals. This paper proposes a lightweight reflection-aware front-end for feature-based stereo VIO. Rather than suppressing all floor-region features, the proposed method estimates the ground height in real time and rejects only feature …
Reliable evaluation of visual 3D reconstruction and depth estimation in vegetation-rich outdoor environments is limited by the scarcity of geometric ground-truth data and the cost of complete scanner surveys. We present a LiDARbased reference-generation pipeline for evaluating the zero-shot performance of feed-forward visual-geometry models alongside conventional structure-from-motion (SfM) methods. The pipeline reuses camera images, LiDAR scans, and reference poses from existing multi-sensor localization datasets to generate per-view depth maps and visible reference point clouds. To address …
@misc{zhong2026visibility,
title = {{Visibility-Aware Reference Generation for Benchmarking Visual 3D Reconstruction in Vegetation-Rich Environments}},
author = {Zhipeng Zhong and Matthew Coombes and Cunjia Liu},
year = {2026},
eprint = {2611.05361},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.05361},
}
We propose PadLoc, a training-free localization back-end that places a moving sensor within a known floor plan. Floor plans are cheap, persistent, and robust to appearance change, but recent learned-depth methods localize against them by filtering per-frame depth through dense $(x,y,\theta)$ pose grids. PadLoc keeps the swappable depth front-end and replaces the dense grid back-end with sparse geometric matching: dominant wall orientations define a small pose-candidate set, masked normalized cross-correlation scores observed free space against the plan, and a moving-pose Gaussian-mixture …
Zhewei Gui, Anthony Bolton, Jiyao Zhang, Zeyuan Chen et al.
Abstract摘要
Dexterous manipulation involves not only moving objects, but also arranging the hand around them to maintain useful contacts and enable subsequent actions. Yet many learning-based systems specify goals primarily through object poses or trajectories, leaving hand-object configurations to emerge implicitly. We introduce DexHOT, which formulates dexterous manipulation as hand-object configuration transfer: moving between feasible configurations that jointly specify hand articulation and object pose relative to the wrist. DexHOT learns a reusable relation-conditioned transfer primitive from …
@misc{gui2026dexhot,
title = {{DexHOT: Learning Hand-Object Configuration Transfer for Dexterous Manipulation}},
author = {Zhewei Gui and Anthony Bolton and Jiyao Zhang and Zeyuan Chen and Qiyang Yan and Tianyu Wang and Hao Dong},
year = {2026},
eprint = {2611.05119},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.05119},
}
Repeated robotic monitoring requires localization across visits to the same environment, even if the environment changes. Such changes can substantially reduce persistent visual content, and repetitive structures can lead to incorrect cross-session correspondences. In this paper, we address visual multi-session registration of a new data recording (the query session) to a previously reconstructed reference map. Under substantial visual and structural changes, cross-session localization may be possible only for parts of the trajectory. In our approach, we therefore rely on a sparse set of …
@misc{erzurumlu2026sparse,
title = {{Sparse Anchors for Visual Multi-Session Registration in Changing Environments}},
author = {Yunus Talha Erzurumlu and Niklas Trekel and Saurabh Gupta and Nico Koltermann and Olga Vysotska and Jens Behley and Louis Wiesmann and Cyrill Stachniss},
year = {2026},
eprint = {2611.05084},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.05084},
}
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 …
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 …
Feature matching underpins many robotic perception tasks, including visual localization, mapping, SLAM, and autonomous navigation. Existing semi-dense matchers predict confidence on fixed grids, limiting correspondences to predefined locations and requiring costly high-resolution grids for precise localization. We present CoReMatch (Coordinate Refinement Match), a recurrent framework that refines correspondences directly in continuous coordinate space rather than predicting discrete confidence maps. CoReMatch progressively improves correspondence estimates by propagating information across …
@misc{wang2026corematch,
title = {{CoReMatch: Recurrent Continuous Coordinate Refinement for Real-Time Robotic Feature Matching}},
author = {Robert J. Wang and Charles Ling and Boyu Wang},
year = {2026},
eprint = {2611.03932},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.03932},
}
Shivangi Rai, Kunal Jangid, Vaibhav Kumar, Vinod K Kurmi
Abstract摘要
Robust 3D point-cloud recognition is critical for robotics, mapping, and urban sensing, yet point-cloud classifiers often suffer performance drops under domain shifts caused by sensor changes, environmental variation, and acquisition artifacts. Many existing adaptation methods are difficult to deploy in practice because they require access to source data or the internal parameters of the source model, which may be restricted by privacy, licensing, or security constraints. We present 3D-BBDA, a backpropagation-free black-box domain adaptation framework that adapts a source-trained predictor to …
@misc{rai2026d,
title = {{3D-BBDA: Backpropagation-Free Black-Box Domain Adaptation for Robust 3D Point Cloud Recognition}},
author = {Shivangi Rai and Kunal Jangid and Vaibhav Kumar and Vinod K Kurmi},
year = {2026},
eprint = {2611.03588},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2611.03588},
}
Yasamin Borhani, Javad Khoramdel, Yang Gao, Po-Chien Luan et al.
Abstract摘要
Estimating the metric 3D position of people from a monocular camera is important for robot navigation and motion prediction. Lightweight pose-based localizers are attractive for robotic hardware with limited computational resources because they operate on compact 2D keypoints. However, they typically discard the richer visual representations computed by the pose estimator. We introduce MoSoLoco, a per-frame monocular 3D human localizer that combines the pose detector's internal visual features with the detected 2D skeleton, without requiring an additional RGB or depth encoder. MoSoLoco can …
@misc{borhani2026mosoloco,
title = {{MoSoLoco: Monocular 3D Human Localization through Visual Latent Features and Social Context}},
author = {Yasamin Borhani and Javad Khoramdel and Yang Gao and Po-Chien Luan and Alexandre Alahi},
year = {2026},
eprint = {2611.03189},
archivePrefix = {arXiv},
primaryClass = {cs.CV},
url = {https://arxiv.org/abs/2611.03189},
}
Field robots operating in mines, tunnels, and disaster areas require reliable localization despite GNSS denial and degraded camera and LiDAR measurements caused by dust, smoke, or poor illumination. Missions involving both ground and aerial robots further motivate complementary sensing modalities that do not depend on visibility, preinstalled infrastructure, or wheel contact. This letter presents MISLAM, a tightly coupled magnetic-inertial simultaneous localization and mapping system using an IMU and a nine-magnetometer array, without relying on external odometry or platform-specific motion …
@misc{huang2026tightly,
title = {{A Tightly Coupled Magnetic-Inertial SLAM System for Field Robots}},
author = {Chuan Huang and Tongxing Peng},
year = {2026},
eprint = {2611.03106},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.03106},
}
Zhongkai Gu, Yang Liu, Wei Zhu, Mitsuhiro Hayashibe
Abstract摘要
Contact transitions allow humanoid robots to redistribute object support across the whole body, enabling manipulation beyond hand-only grasps. Human videos provide a scalable source of such transitions for robots to learn from. However, body occlusion disrupts object pose tracking and corrupts retargeted motion. Moreover, accurately reproducing the object trajectory does not ensure that the robot applies stabilizing forces at the intended contacts, risking slips or drops in later phases. To address these challenges, we propose ReContact, which reconstructs and retargets human-object …
@misc{gu2026recontact,
title = {{ReContact: Reconstruct and Retarget Human Contacts from Video for Contact-Rich Humanoid Manipulation}},
author = {Zhongkai Gu and Yang Liu and Wei Zhu and Mitsuhiro Hayashibe},
year = {2026},
eprint = {2611.02968},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.02968},
}
Yuxin Chen, Wenxuan Wang, Wanwen Chen, Qi Zeng et al.
Abstract摘要
Purpose: Blended augmented reality (AR) overlays can provide ambiguous depth cues in which subsurface anatomy floats above the tissue surface. We investigate whether an interactive 3D cutaway visualization can improve robot-assisted target localization. Methods: We propose Virtual Box, an interactive 3D cutaway interface that allows users to independently manipulate the viewing perspective to inspect subsurface targets. In a controlled, counterbalanced within-subject tissue phantom study, 15 engineering students used Virtual Box and a depth-enhanced blended AR overlay to position a da Vinci …
@misc{chen2026interactive,
title = {{Interactive 3D Cutaway Visualization for Subsurface Target Localization in Robot-Assisted Surgery}},
author = {Yuxin Chen and Wenxuan Wang and Wanwen Chen and Qi Zeng and Septimiu E. Salcudean},
year = {2026},
eprint = {2611.02537},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.02537},
}
Arjun Bhardwaj, Mayank Mittal, Maximum Wilder-Smith, Vaishakh Patil et al.
Abstract摘要
Dexterous in-hand manipulation is commonly formulated around explicit object pose estimation, yet reliable pose tracking is challenging under severe hand-object occlusions and often requires object-specific supervision. This dependence creates a bottleneck between perception and control that can limit robustness and scalability. We present an end-to-end visuomotor framework for dexterous in-hand reorientation that operates on RGB observations and proprioception without intermediate pose estimation. Our approach jointly learns visual representations and control policies through behavior …
@misc{bhardwaj2026goaldex,
title = {{GoalDex: Learning Image-Goal-Conditioned Policies for Dexterous In-Hand Manipulation}},
author = {Arjun Bhardwaj and Mayank Mittal and Maximum Wilder-Smith and Vaishakh Patil and Marco Hutter},
year = {2026},
eprint = {2611.02171},
archivePrefix = {arXiv},
primaryClass = {cs.RO},
url = {https://arxiv.org/abs/2611.02171},
}