机器人 / 具身智能 - arXivDaily 专题

2108.03298 2021-09-28 cs.RO cs.AI cs.LG 82%

What Matters in Learning from Offline Human Demonstrations for Robot Manipulation

Ajay Mandlekar, Danfei Xu, Josiah Wong, Soroush Nasiriany, Chen Wang, Rohun Kulkarni, Li Fei-Fei, Silvio Savarese, Yuke Zhu, Roberto Martín-Martín

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

Comments CoRL 2021 (Oral)

2107.08942 2021-07-20 cs.RO cs.AI cs.LG 82%

Untangling Dense Non-Planar Knots by Learning Manipulation Features and Recovery Policies

Priya Sundaresan, Jennifer Grannen, Brijen Thananjeyan, Ashwin Balakrishna, Jeffrey Ichnowski, Ellen Novoseller, Minho Hwang, Michael Laskey, Joseph E. Gonzalez, Ken Goldberg

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

2009.05859 2021-02-02 cs.RO cs.AI cs.LG 82%

Towards Automatic Manipulation of Intra-cardiac Echocardiography Catheter

Young-Ho Kim, Jarrod Collins, Zhongyu Li, Ponraj Chinnadurai, Ankur Kapoor, C. Huie Lin, Tommaso Mansi

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

2011.06813 2020-11-16 cs.RO cs.CV cs.LG 82%

Learning Object Manipulation Skills via Approximate State Estimation from Real Videos

Vladimír Petrík, Makarand Tapaswi, Ivan Laptev, Josef Sivic

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

Comments CoRL 2020, code at CoRL2020" target="_blank" rel="noopener">https://github.com/makarandtapaswi/Real2Sim_CoRL2020, project page at https://data.ciirc.cvut.cz/public/projects/2020Real2Sim/

2010.12083 2020-10-26 cs.RO cs.CL cs.CV cs.LG 82%

Language-Conditioned Imitation Learning for Robot Manipulation Tasks

Simon Stepputtis, Joseph Campbell, Mariano Phielipp, Stefan Lee, Chitta Baral, Heni Ben Amor

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

Comments Accepted to the 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada as spotlight presentation

2002.06806 2020-10-05 cs.LG cs.AI cs.CV 82%

Reinforcement learning for the privacy preservation and manipulation of eye tracking data

Wolfgang Fuhl, Efe Bozkir, Enkelejda Kasneci

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

2008.09377 2020-08-24 cs.LG cs.AI cs.NE cs.RO stat.ML 82%

Curriculum Learning with Hindsight Experience Replay for Sequential Object Manipulation Tasks

Binyamin Manela, Armin Biess

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

Comments arXiv admin note: text overlap with arXiv:2001.03877

2006.03201 2020-06-08 cs.CV cs.AI cs.RO 82%

Egocentric Object Manipulation Graphs

Eadom Dessalene, Michael Maynord, Chinmaya Devaraj, Cornelia Fermuller, Yiannis Aloimonos

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

2005.10430 2020-05-22 cs.CV cs.AI cs.LG 82%

Gender Slopes: Counterfactual Fairness for Computer Vision Models by Attribute Manipulation

Jungseock Joo, Kimmo Kärkkäinen

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

2001.00991 2020-01-07 cs.RO cs.AI cs.HC cs.LG cs.SY eess.SY 82%

Human-robot co-manipulation of extended objects: Data-driven models and control from analysis of human-human dyads

Erich Mielke, Eric Townsend, David Wingate, Marc D. Killpack

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

Comments Paper has been in submission to IJRR since November 2018

1911.04676 2019-11-13 cs.RO cs.AI cs.DS cs.LG cs.SY eess.SY 82%

Prediction of Bottleneck Points for Manipulation Planning in Cluttered Environment using a 3D Convolutional Neural Network

Indraneel Patil, B. K. Rout, V. Kalaichelvi

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

Comments 7 pages, 12 figures

1902.02041 2019-11-04 cs.LG cs.AI cs.CV stat.ML 82%

Fooling Neural Network Interpretations via Adversarial Model Manipulation

Juyeon Heo, Sunghwan Joo, Taesup Moon

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

Journal ref NeurIPS 2019, ICCV workshop 2019

1908.05224 2019-10-09 cs.RO cs.AI cs.LG 82%

Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real

Ofir Nachum, Michael Ahn, Hugo Ponte, Shixiang Gu, Vikash Kumar

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

1909.00684 2019-09-04 cond-mat.soft physics.app-ph 82%

Shear-wave manipulation by embedded soft devices

Linli Chen, Chao Ma, Pingping Zheng, Qian Zhao, Zheng Chang

专题命中机器人操作：manipulation(title,abstract)；robotics(abstract)

Comments 20 pages, 6 figures

1903.12302 2019-04-01 cs.RO cs.AI cs.CV 82%

Amortized Object and Scene Perception for Long-term Robot Manipulation

Ferenc Balint-Benczedi, Michael Beetz

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

1810.10654 2018-10-26 cs.RO cs.AI cs.LG 82%

Sample-Efficient Learning of Nonprehensile Manipulation Policies via Physics-Based Informed State Distributions

Lerrel Pinto, Aditya Mandalika, Brian Hou, Siddhartha Srinivasa

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

1809.04322 2018-09-13 cs.RO cs.AI cs.LG 82%

Reinforcement Learning in Topology-based Representation for Human Body Movement with Whole Arm Manipulation

Weihao Yuan, Kaiyu Hang, Haoran Song, Danica Kragic, Michael Y. Wang, Johannes A. Stork

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

Comments Submitted to RA-L with ICRA 2019

1806.09266 2018-06-26 cs.RO cs.CV cs.LG stat.ML 82%

Learning Task-Oriented Grasping for Tool Manipulation from Simulated Self-Supervision

Kuan Fang, Yuke Zhu, Animesh Garg, Andrey Kurenkov, Viraj Mehta, Li Fei-Fei, Silvio Savarese

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

Comments RSS 2018

1705.08475 2017-11-07 cs.LG cs.AI cs.CV stat.ML 82%

Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation

Matthias Hein, Maksym Andriushchenko

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

Comments final version accepted at NIPS 2017, fixed bug in implementation of Cross-Lipschitz regularization and lower bound computation, now results are better

1703.07255 2017-03-23 cs.CV cs.AI cs.GR cs.LG stat.ML 82%

ZM-Net: Real-time Zero-shot Image Manipulation Network

Hao Wang, Xiaodan Liang, Hao Zhang, Dit-Yan Yeung, Eric P. Xing

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

1601.00741 2016-01-06 cs.RO cs.AI cs.LG 82%

Learning Preferences for Manipulation Tasks from Online Coactive Feedback

Ashesh Jain, Shikhar Sharma, Thorsten Joachims, Ashutosh Saxena

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

Comments IJRR accepted (Learning preferences over trajectories from coactive feedback)

1301.3592 2014-08-22 cs.LG cs.CV cs.RO 82%

Deep Learning for Detecting Robotic Grasps

Ian Lenz, Honglak Lee, Ashutosh Saxena

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

Comments Current version was accepted to IJRR Special Issue on Robot Vision 2014 Workshop version accepted to ICLR 2013. Conference version accepted to RSS 2013

0903.4930 2009-12-01 cs.AI cs.LG cs.RO 82%

Time manipulation technique for speeding up reinforcement learning in simulations

Petar Kormushev, Kohei Nomoto, Fangyan Dong, Kaoru Hirota

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

Comments 12 pages

Journal ref International Journal of Cybernetics and Information Technologies, vol. 8, no. 1, pp. 12-24, 2008

2608.20114 2026-08-24 cs.AI cs.RO 版本更新 82%

DECOWAM: Decoupled Whole-Body World-Action Model for Legged Mobile Manipulation

DECOWAM：用于腿式移动操作的解耦全身世界-动作模型

Siyuan Ma, Boshi Zhang, Yutian Zhang, Qinglian Wu, Jiaqi Zhai, Dong Wei, Qiaojun Yu

机构 * Tsinghua University（清华大学）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）； Harbin Institute of Technology（哈尔滨工业大学）； Hangzhou Yunshenchu Technology Co., Ltd. (DEEP Robotics)（杭州云神初科技有限公司（深智机器人））

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

AI总结本研究提出DECOWAM模型，通过解耦全身动作因素提升移动操作的视觉与动作预测性能，在真实机器人数据集ARMDOG上验证了其在协调性和鲁棒性上的优势。

Comments 8 pages, 5 figures. Introduces DECOWAM, a decoupled whole-body world-action model for legged mobile manipulation, and the ARMDOG real-robot dataset

2608.07045 2026-08-10 cs.RO cs.CV 新提交 82%

C2Dex: Contact-Consistent Reconstruction and Retargeting for Dexterous Manipulation from Monocular Video

C2Dex：基于单目视频的接触一致性重建与灵巧操作重定向

Jie Ren, Zhehao Jiang, Yinhong Yang, Haorui Jia, Han Jiang, Ben Li, Yao Yao, Cheng Lin, Qiu Shen, Zhenshan Bing, Xiao-Xiao Long, Xun Cao

机构 * Nanjing University（南京大学）； China Mobile Research Institute（中国移动研究院）

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

AI总结 C2Dex是基于单目视频的灵巧操作框架，通过聚合物体侧稳定接触实现HOI重建与手物几何保留，在DexYCB、TACO上的轨迹成功率显著优于基线，且真实机器人复现可行。

Comments 9 pages, 5 figures. Submitted to IEEE Robotics and Automation Letters (RA-L). Project page: https://k-jie.github.io/C2Dex/

2606.06761 2026-06-08 cs.RO cs.AI 新提交 82%

AxisGuide: Grounding Robot Action Coordinate System in RGB Observations for Robust Visuomotor Manipulation

AxisGuide: 在RGB观测中接地机器人动作坐标系以实现鲁棒的视觉运动操控

Jiyun Jang, Yujin Sung, Woosung Joung, Daewon Chae, Sangwon Lee, Sohwi Kim, Jinkyu Kim, Jungbeom Lee

机构 * Korea University（韩国大学）； University of Michigan（密歇根大学）； KT R&D Center（KT研发中心）； Kakao Mobility（Kakao移动）

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

AI总结针对视觉运动策略在分布偏移下动作执行失败的问题，提出AxisGuide方法，通过渲染机器人基座坐标系轴并叠加提示通道，增强动作坐标理解，显著提升泛化性能。

Comments Accepted to Robotics: Science and Systems (RSS) 2026

2506.04646 2026-05-15 cs.RO cs.LG 82%

ActivePusher: Active Learning and Planning with Residual Physics for Nonprehensile Manipulation

ActivePusher: 基于残差物理的主动学习与规划用于非抓取操作

Zhuoyun Zhong, Seyedali Golestaneh, Constantinos Chamzas

机构 * Department of Robotics Engineering, Worcester Polytechnic Institute (WPI)（机器人工程系，沃斯特理工学院（WPI））

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

AI总结本文提出ActivePusher框架，结合残差物理模型与不确定性主动学习，提升非抓取操作的数据效率和规划成功率。

Comments Accepted by the 2026 IEEE International Conference on Robotics & Automation (ICRA 2026)

2502.18615 2026-03-11 cs.RO cs.LG 82%

A Distributional Treatment of Real2Sim2Real for Object-Centric Agent Adaptation in Vision-Driven Deformable Linear Object Manipulation

基于分布的实-仿-实方法用于视觉驱动的可变形线性物体操控中的对象中心智能体适应

Georgios Kamaras, Subramanian Ramamoorthy

机构 * School of Informatics, The University of Edinburgh（信息学院，爱丁堡大学）

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

AI总结本文提出基于分布的实-仿-实方法，通过视觉感知操控可变形线性物体，利用无需模型推断进行域随机化训练，实现无微调的现实应用。

Journal ref In IEEE Robotics and Automation Letters, Volume 10, Issue 8, August 2025, Pages 8075-8082

2601.10827 2026-01-19 cs.RO cs.AI cs.SY eess.SY 82%

Approximately Optimal Global Planning for Contact-Rich SE(2) Manipulation on a Graph of Reachable Sets

近似最优的接触丰富SE(2)操作在可达集图上的全局规划

Simin Liu, Tong Zhao, Bernhard Paus Graesdal, Peter Werner, Jiuguang Wang, John Dolan, Changliu Liu, Tao Pang

机构 * Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人学院）； Robotics and AI Institute（机器人与人工智能研究所）； CSAIL, Massachusetts Institute of Technology（麻省理工学院计算机科学与人工智能实验室）

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

AI总结本文提出了一种近似最优的接触丰富SE(2)操作全局规划方法，通过构建可达集图实现高效运动规划，显著提升了任务效率和成功率。

Comments 17 pages, 14 figures; under submission to IEEE Transactions on Robotics

2210.00858 2025-12-16 cs.RO cs.AI cs.HC 82%

Enhancing Interpretability and Interactivity in Robot Manipulation: A Neurosymbolic Approach

提升机器人操作的可解释性和交互性：一种神经符号方法

Georgios Tziafas, Hamidreza Kasaei

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

AI总结本文提出一种神经符号方法，通过结合语言引导的视觉推理与机器人操作，提升可解释性和交互性，实现80.2%的成功率。

Comments Published in International Journal of Robotics Research (IJRR) (2025)

1. 机器人操作 22125 篇

What Matters in Learning from Offline Human Demonstrations for Robot Manipulation

Untangling Dense Non-Planar Knots by Learning Manipulation Features and Recovery Policies

Towards Automatic Manipulation of Intra-cardiac Echocardiography Catheter

Learning Object Manipulation Skills via Approximate State Estimation from Real Videos

Language-Conditioned Imitation Learning for Robot Manipulation Tasks

Reinforcement learning for the privacy preservation and manipulation of eye tracking data

Curriculum Learning with Hindsight Experience Replay for Sequential Object Manipulation Tasks

Egocentric Object Manipulation Graphs

Gender Slopes: Counterfactual Fairness for Computer Vision Models by Attribute Manipulation

Human-robot co-manipulation of extended objects: Data-driven models and control from analysis of human-human dyads

Prediction of Bottleneck Points for Manipulation Planning in Cluttered Environment using a 3D Convolutional Neural Network

Fooling Neural Network Interpretations via Adversarial Model Manipulation

Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real

Shear-wave manipulation by embedded soft devices

Amortized Object and Scene Perception for Long-term Robot Manipulation

Sample-Efficient Learning of Nonprehensile Manipulation Policies via Physics-Based Informed State Distributions

Reinforcement Learning in Topology-based Representation for Human Body Movement with Whole Arm Manipulation

Learning Task-Oriented Grasping for Tool Manipulation from Simulated Self-Supervision

Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation

ZM-Net: Real-time Zero-shot Image Manipulation Network

Learning Preferences for Manipulation Tasks from Online Coactive Feedback

Deep Learning for Detecting Robotic Grasps

Time manipulation technique for speeding up reinforcement learning in simulations

DECOWAM: Decoupled Whole-Body World-Action Model for Legged Mobile Manipulation

C2Dex: Contact-Consistent Reconstruction and Retargeting for Dexterous Manipulation from Monocular Video

AxisGuide: Grounding Robot Action Coordinate System in RGB Observations for Robust Visuomotor Manipulation

ActivePusher: Active Learning and Planning with Residual Physics for Nonprehensile Manipulation

A Distributional Treatment of Real2Sim2Real for Object-Centric Agent Adaptation in Vision-Driven Deformable Linear Object Manipulation

Approximately Optimal Global Planning for Contact-Rich SE(2) Manipulation on a Graph of Reachable Sets

Enhancing Interpretability and Interactivity in Robot Manipulation: A Neurosymbolic Approach