机器人 / 具身智能 - arXivDaily 专题

2503.01238 2026-02-09 cs.RO cs.AI cs.LG 85%

A Taxonomy for Evaluating Generalist Robot Manipulation Policies

机器人通用操作策略评估的分类

Jensen Gao, Suneel Belkhale, Sudeep Dasari, Ashwin Balakrishna, Dhruv Shah, Dorsa Sadigh

专题命中机器人操作：manipulation(title,abstract)；robotics(abstract,comments)；分类 cs.RO、cs.AI、cs.LG

AI总结本文提出STAR-Gen分类，旨在系统化评估机器人操作策略的泛化能力，通过视觉、语义和行为三个维度，结合现实案例研究揭示泛化评估的挑战与改进方向。

Comments IEEE Robotics and Automation Letters (RA-L)

2410.10803 2025-09-10 cs.RO cs.CV cs.LG 85%

Generalizable Humanoid Manipulation with 3D Diffusion Policies

Yanjie Ze, Zixuan Chen, Wenhao Wang, Tianyi Chen, Xialin He, Ying Yuan, Xue Bin Peng, Jiajun Wu

机构 * Stanford University（斯坦福大学）； Simon Fraser University（西蒙 Fraser大学）； UPenn（宾夕法尼亚大学）； UIUC（伊利诺伊大学香槟分校）； CMU（卡内基梅隆大学）

专题命中机器人操作：manipulation(title,abstract)；robotic(abstract)；分类 cs.RO、cs.CV、cs.LG

Comments IROS 2025. Project website: https://humanoid-manipulation.github.io

2406.19464 2024-11-05 cs.RO cs.AI cs.CV cs.SD eess.AS 85%

ManiWAV: Learning Robot Manipulation from In-the-Wild Audio-Visual Data

Zeyi Liu, Cheng Chi, Eric Cousineau, Naveen Kuppuswamy, Benjamin Burchfiel, Shuran Song

专题命中机器人操作：manipulation(title,abstract)；robot learning(abstract,comments)；分类 cs.RO、cs.AI、cs.CV

Comments Conference on Robot Learning (CoRL) 2024; Project website: https://maniwav.github.io/

2409.07914 2024-10-17 cs.RO cs.AI cs.CV 85%

InterACT: Inter-dependency Aware Action Chunking with Hierarchical Attention Transformers for Bimanual Manipulation

Andrew Lee, Ian Chuang, Ling-Yuan Chen, Iman Soltani

专题命中机器人操作：manipulation(title,abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.CV；robot learning(comments)

Comments Accepted at Conference on Robot Learning (CoRL) 2024

2410.06158 2024-10-10 cs.RO cs.CV cs.LG 85%

GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation

Chi-Lam Cheang, Guangzeng Chen, Ya Jing, Tao Kong, Hang Li, Yifeng Li, Yuxiao Liu, Hongtao Wu, Jiafeng Xu, Yichu Yang, Hanbo Zhang, Minzhao Zhu

专题命中机器人操作：manipulation(title,abstract)；robotic(abstract)；分类 cs.RO、cs.CV、cs.LG

Comments Tech Report. Authors are listed in alphabetical order. Project page: https://gr2-manipulation.github.io

2306.07392 2024-05-30 cs.RO cs.CV cs.LG 85%

Learning Any-View 6DoF Robotic Grasping in Cluttered Scenes via Neural Surface Rendering

Snehal Jauhri, Ishikaa Lunawat, Georgia Chalvatzaki

专题命中机器人操作：robotic(title,abstract)；manipulation(abstract)；分类 cs.RO、cs.CV、cs.LG；robotics(comments)

Comments Accpeted at Robotics: Science and Systems 2024

2309.01087 2023-10-31 cs.RO cs.AI cs.LG 85%

Stabilize to Act: Learning to Coordinate for Bimanual Manipulation

Jennifer Grannen, Yilin Wu, Brandon Vu, Dorsa Sadigh

专题命中机器人操作：manipulation(title,abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG；robot learning(comments)

Comments Conference on Robot Learning, 2023

2309.13224 2023-10-10 cs.RO cs.AI cs.LG 85%

Pick Planning Strategies for Large-Scale Package Manipulation

Shuai Li, Azarakhsh Keipour, Kevin Jamieson, Nicolas Hudson, Sicong Zhao, Charles Swan, Kostas Bekris

专题命中机器人操作：manipulation(title,abstract)；robotics(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Learning Meets Model-based Methods for Manipulation and Grasping Workshop

2305.04866 2023-09-29 cs.RO cs.AI cs.LG 85%

Causal Policy Gradient for Whole-Body Mobile Manipulation

Jiaheng Hu, Peter Stone, Roberto Martín-Martín

专题命中机器人操作：manipulation(title,abstract)；navigation(abstract)；分类 cs.RO、cs.AI、cs.LG；robotics(journal_ref)

Journal ref Robotics: science and systems. 2023

2309.14463 2023-09-27 cs.RO cs.AI cs.LG 85%

DefGoalNet: Contextual Goal Learning from Demonstrations For Deformable Object Manipulation

Bao Thach, Tanner Watts, Shing-Hei Ho, Tucker Hermans, Alan Kuntz

专题命中机器人操作：manipulation(title,abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG；robotics(comments)

Comments Submitted to IEEE Conference on Robotics and Automation (ICRA) 2024. 8 pages, 11 figures

2306.16700 2023-07-03 cs.RO cs.CV cs.LG 85%

Dynamic-Resolution Model Learning for Object Pile Manipulation

Yixuan Wang, Yunzhu Li, Katherine Driggs-Campbell, Li Fei-Fei, Jiajun Wu

专题命中机器人操作：manipulation(title,abstract)；robotic(abstract)；分类 cs.RO、cs.CV、cs.LG；robotics(comments)

Comments Accepted to Robotics: Science and Systems (RSS) 2023. The first two authors contributed equally. Project Page: https://robopil.github.io/dyn-res-pile-manip

2304.01159 2023-04-04 cs.RO cs.AI cs.LG 85%

DribbleBot: Dynamic Legged Manipulation in the Wild

Yandong Ji, Gabriel B. Margolis, Pulkit Agrawal

专题命中机器人操作：manipulation(title,abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG；robotics(comments)

Comments To appear at the IEEE Conference on Robotics and Automation (ICRA), 2023. Video is available at https://gmargo11.github.io/dribblebot/

2002.09107 2021-04-02 cs.RO cs.CV cs.LG 85%

Learning Precise 3D Manipulation from Multiple Uncalibrated Cameras

Iretiayo Akinola, Jacob Varley, Dmitry Kalashnikov

专题命中机器人操作：manipulation(title,abstract)；robotic(abstract)；分类 cs.RO、cs.CV、cs.LG；robotics(comments)

Comments Accepted at International Conference on Robotics and Automation (ICRA 2020)

1901.00811 2020-12-15 cs.RO cs.AI cs.LG 85%

From exploration to control: learning object manipulation skills through novelty search and local adaptation

Seungsu Kim, Alexandre Coninx, Stephane Doncieux

专题命中机器人操作：manipulation(title,abstract)；robot learning(abstract)；分类 cs.RO、cs.AI、cs.LG；robotics(comments)

Comments 30 pages, 18 figures, accepted for publication in Robotics and Autonomous Systems

2006.01797 2020-09-22 cs.RO cs.CV cs.LG 85%

Object-Independent Human-to-Robot Handovers using Real Time Robotic Vision

Patrick Rosenberger, Akansel Cosgun, Rhys Newbury, Jun Kwan, Valerio Ortenzi, Peter Corke, Manfred Grafinger

专题命中机器人操作：robotic(title,abstract)；manipulation(abstract)；分类 cs.RO、cs.CV、cs.LG；robotics(comments)

Comments IEEE Robotics and Automation Letters (RA-L). Preprint Version. Accepted September, 2020. The code and videos can be found at https://patrosat.github.io/h2r_handovers/

2007.15375 2020-07-31 cs.RO cs.AI cs.LG 85%

Bayesian Optimization for Developmental Robotics with Meta-Learning by Parameters Bounds Reduction

Maxime Petit, Emmanuel Dellandrea, Liming Chen

专题命中机器人操作：robotics(title,abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments Accepted at the IEEE International Conference on Development and Learning and Epigenetic Robotics 2020 (ICDL-Epirob 2020)

2003.01835 2020-03-05 cs.RO cs.CV cs.LG 85%

Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data

Priya Sundaresan, Jennifer Grannen, Brijen Thananjeyan, Ashwin Balakrishna, Michael Laskey, Kevin Stone, Joseph E. Gonzalez, Ken Goldberg

专题命中机器人操作：manipulation(title,abstract)；robotic(abstract)；分类 cs.RO、cs.CV、cs.LG；robotics(journal_ref)

Journal ref 2020 International Conference on Robotics and Automation

1806.07851 2018-10-09 cs.RO cs.AI cs.LG 85%

Sim-to-Real Reinforcement Learning for Deformable Object Manipulation

Jan Matas, Stephen James, Andrew J. Davison

专题命中机器人操作：manipulation(title,abstract)；robot learning(abstract,comments)；分类 cs.RO、cs.AI、cs.LG

Comments Published at the Conference on Robot Learning (CoRL) 2018

1703.02018 2017-03-07 cs.CV cs.LG cs.RO 85%

Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation

Ashvin Nair, Dian Chen, Pulkit Agrawal, Phillip Isola, Pieter Abbeel, Jitendra Malik, Sergey Levine

专题命中机器人操作：manipulation(title,abstract)；robotics(abstract,comments)；分类 cs.RO、cs.CV、cs.LG

Comments 8 pages, accepted to International Conference on Robotics and Automation (ICRA) 2017

2607.07608 2026-07-09 cs.RO cs.CV 新提交 85%

Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation

用于机器人操作的视觉-语言-动作模型中的双潜记忆

Hongyu Qu, Jianzhe Gao, Xiaobin Hu, Shaohuan Yang, Xinlei Yu, Rui Yan, Wenguan Wang, Xiangbo Shu, Shuicheng Yan

机构 * Nanjing University of Science and Technology（南京理工大学）； Zhejiang University（浙江大学）； National University of Singapore（新加坡国立大学）

专题命中机器人操作：manipulation(title)；robotic(title)；分类 cs.RO、cs.CV

AI总结研究针对主流VLA模型处理长期任务的不足，提出LaMem-VLA框架，通过四个协调组件将历史经验重构为潜记忆令牌并与VLA推理直接交织，实现在同一潜空间处理历史经验，经实验验证该框架具有优越性。

Comments Project page: https://github.com/quhongyu/LaMem-VLA

2606.08657 2026-06-09 cs.RO cs.AI 新提交 85%

Latent Diffusion Policy: Shaping Latent Spaces for Diffusion-Based Robotic Manipulation

潜在扩散策略：为基于扩散的机器人操作塑造潜在空间

Zhexuan Zhou, Yichen Lai, Jinhao Zhang, Huizhe Li, Youmin Gong, Jie Mei

机构 * National University of Singapore（新加坡国立大学）； University of Science and Technology of China（中国科学技术大学）

专题命中机器人操作：manipulation(title)；robotic(title)；分类 cs.RO、cs.AI

AI总结提出两阶段框架LDP，通过CVAE编码器吸收场景理解，在预浓缩的潜在空间中进行流匹配，简化学习并提升多臂协调任务性能。

2605.07381 2026-05-11 cs.RO cs.AI 85%

Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation

通过锚点中心适应摆脱机器人操作中的多样性陷阱

Yanzhe Chen, Kevin Yuchen Ma, Qi Lv, Yiqi Lin, Zechen Bai, Chen Gao, Mike Zheng Shou

机构 * National University of Singapore（新加坡国立大学）； Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））； Institude for Information Research, A STAR（A*STAR信息研究所）

专题命中机器人操作：manipulation(title)；robotic(title)；分类 cs.RO、cs.AI

AI总结本文提出锚点中心适应方法，通过稳定策略骨架和选择性扩展覆盖范围，解决多样性陷阱问题，提升任务可靠性和成功率。

Comments 21 pages, 8 figures

2507.05627 2025-07-09 cs.RO cs.CV 85%

DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation

Young Hun Kim, Seungyeon Kim, Yonghyeon Lee, Frank Chongwoo Park

机构 * Seoul National University（首尔国立大学）； Massachusetts Institute of Technology（麻省理工学院）

专题命中机器人操作：manipulation(title)；robotic(title)；分类 cs.RO、cs.CV

2503.21257 2025-03-28 cs.RO cs.AI 85%

OminiAdapt: Learning Cross-Task Invariance for Robust and Environment-Aware Robotic Manipulation

Yongxu Wang, Weiyun Yi, Xinhao Kong, Wanting Li

专题命中机器人操作：manipulation(title)；robotic(title)；分类 cs.RO、cs.AI

2405.01192 2024-05-03 cs.RO cs.CV 85%

Imagine2touch: Predictive Tactile Sensing for Robotic Manipulation using Efficient Low-Dimensional Signals

Abdallah Ayad, Adrian Röfer, Nick Heppert, Abhinav Valada

专题命中机器人操作：manipulation(title)；robotic(title)；分类 cs.RO、cs.CV

Comments 3 pages, 3 figures, 2 tables, accepted at ViTac2024 ICRA2024 Workshop. arXiv admin note: substantial text overlap with arXiv:2403.15107

2301.03003 2023-01-10 cs.RO cs.AI 85%

Foldsformer: Learning Sequential Multi-Step Cloth Manipulation With Space-Time Attention

Kai Mo, Chongkun Xia, Xueqian Wang, Yuhong Deng, Xuehai Gao, Bin Liang

专题命中机器人操作：manipulation(title,abstract)；robotic(abstract)；robotics(comments,journal_ref)；分类 cs.RO、cs.AI

Comments 8 pages, 6 figures, published to IEEE Robotics & Automation Letters (RA-L)

Journal ref IEEE Robotics and Automation Letters, vol. 8, no. 2, pp. 760-767, Feb. 2023

2011.12805 2021-11-23 cs.CV cs.RO 85%

Fast Object Segmentation Learning with Kernel-based Methods for Robotics

Federico Ceola, Elisa Maiettini, Giulia Pasquale, Lorenzo Rosasco, Lorenzo Natale

专题命中机器人操作：robotics(title,abstract)；manipulation(abstract)；分类 cs.RO、cs.CV

Comments Manuscript accepted to 2021 IEEE International Conference on Robotics and Automation (ICRA)

Journal ref IEEE International Conference on Robotics and Automation (ICRA), 2021

2105.09067 2021-05-20 cs.CV cs.RO 85%

Localization and Tracking of User-Defined Points on Deformable Objects for Robotic Manipulation

Sven Dittus, Benjamin Alt, Andreas Hermann, Darko Katic, Rainer Jäkel, Jürgen Fleischer

专题命中机器人操作：manipulation(title)；robotic(title)；分类 cs.RO、cs.CV

Comments 4 pages, 4 figures, accepted at the ICRA 2021 Workshop on Representing and Manipulating Deformable Objects

2510.02526 2025-10-06 cs.RO 85%

U-LAG: Uncertainty-Aware, Lag-Adaptive Goal Retargeting for Robotic Manipulation

Anamika J H, Anujith Muraleedharan

机构 * Anamika J H（匿名ika J H）； Anujith Muraleedharan（阿努吉斯·穆拉莱德哈兰）

专题命中机器人操作：manipulation(title,comments)；robotic(title)；分类 cs.RO

Comments 8 pages, 5 figures. Accepted to the IROS 2025 Workshop on Perception and Planning for Mobile Manipulation in Changing Environments

2501.02303 2025-01-07 cs.RO eess.SP 85%

Design and Benchmarking of A Multi-Modality Sensor for Robotic Manipulation with GAN-Based Cross-Modality Interpretation

Dandan Zhang, Wen Fan, Jialin Lin, Haoran Li, Qingzheng Cong, Weiru Liu, Nathan F. Lepora, Shan Luo

专题命中机器人操作：manipulation(title)；robotic(title)；分类 cs.RO；robotics(comments)

Comments Accepted by IEEE Transactions on Robotics

1. 机器人操作 22015 篇

A Taxonomy for Evaluating Generalist Robot Manipulation Policies

Generalizable Humanoid Manipulation with 3D Diffusion Policies

ManiWAV: Learning Robot Manipulation from In-the-Wild Audio-Visual Data

InterACT: Inter-dependency Aware Action Chunking with Hierarchical Attention Transformers for Bimanual Manipulation

GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation

Learning Any-View 6DoF Robotic Grasping in Cluttered Scenes via Neural Surface Rendering

Stabilize to Act: Learning to Coordinate for Bimanual Manipulation

Pick Planning Strategies for Large-Scale Package Manipulation

Causal Policy Gradient for Whole-Body Mobile Manipulation

DefGoalNet: Contextual Goal Learning from Demonstrations For Deformable Object Manipulation

Dynamic-Resolution Model Learning for Object Pile Manipulation

DribbleBot: Dynamic Legged Manipulation in the Wild

Learning Precise 3D Manipulation from Multiple Uncalibrated Cameras

From exploration to control: learning object manipulation skills through novelty search and local adaptation

Object-Independent Human-to-Robot Handovers using Real Time Robotic Vision

Bayesian Optimization for Developmental Robotics with Meta-Learning by Parameters Bounds Reduction

Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data

Sim-to-Real Reinforcement Learning for Deformable Object Manipulation

Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation

Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation

Latent Diffusion Policy: Shaping Latent Spaces for Diffusion-Based Robotic Manipulation

Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation

DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation

OminiAdapt: Learning Cross-Task Invariance for Robust and Environment-Aware Robotic Manipulation

Imagine2touch: Predictive Tactile Sensing for Robotic Manipulation using Efficient Low-Dimensional Signals

Foldsformer: Learning Sequential Multi-Step Cloth Manipulation With Space-Time Attention

Fast Object Segmentation Learning with Kernel-based Methods for Robotics

Localization and Tracking of User-Defined Points on Deformable Objects for Robotic Manipulation

U-LAG: Uncertainty-Aware, Lag-Adaptive Goal Retargeting for Robotic Manipulation

Design and Benchmarking of A Multi-Modality Sensor for Robotic Manipulation with GAN-Based Cross-Modality Interpretation