机器人 / 具身智能 - arXivDaily 专题

1905.04427 2019-05-14 cs.RO 83%

Fast Skill Learning for Variable Compliance Robotic Assembly

Tianyu Ren, Yunfei Dong, Dan Wu, Ken Chen

专题命中机器人学习：robotic(title,abstract)；manipulation(abstract)；分类 cs.RO

Comments 10 pages, 5 figures

1801.10321 2018-10-17 cs.RO 83%

Constraint Estimation and Derivative-Free Recovery for Robot Learning from Demonstrations

Jonathan Lee, Michael Laskey, Roy Fox, Ken Goldberg

专题命中机器人学习：robot learning(title)；manipulation(abstract)；robotic(abstract)；分类 cs.RO

1809.10797 2018-10-01 cs.RO 83%

Collaborative Robot Learning from Demonstrations using Hidden Markov Model State Distribution

Sulabh Kumra, Ferat Sahin

专题命中机器人学习：robot learning(title,abstract)；robotics(abstract)；分类 cs.RO

1808.05525 2018-08-17 cs.RO cs.NE 83%

Experiential Robot Learning with Accelerated Neuroevolution

Ahmed Aly, Joanne B. Dugan

专题命中机器人学习：robot learning(title,abstract)；robotic(abstract)；分类 cs.RO

1711.09055 2017-11-27 cs.RO cs.AI cs.CL cs.CV cs.LG 83%

Interactive Robot Learning of Gestures, Language and Affordances

Giovanni Saponaro, Lorenzo Jamone, Alexandre Bernardino, Giampiero Salvi

专题命中机器人学习：robot learning(title)；robotics(abstract)；分类 cs.RO、cs.AI、cs.CV

Comments code available at https://github.com/gsaponaro/glu-gestures

Journal ref International Workshop on Grounding Language Understanding (GLU), Satellite of Interspeech 2017

1710.08789 2017-10-25 cs.RO 83%

A survey of robot learning from demonstrations for Human-Robot Collaboration

Jangwon Lee

专题命中机器人学习：robot learning(title,abstract)；robotics(abstract)；分类 cs.RO

2505.03296 2026-06-11 cs.RO cs.AI cs.LG 版本更新 83%

The Unreasonable Effectiveness of Discrete-Time Gaussian Process Mixtures for Robot Policy Learning

离散时间高斯过程混合在机器人策略学习中的惊人有效性

Jan Ole von Hartz, Adrian Röfer, Joschka Boedecker, Abhinav Valada

机构 * Department of Computer Science, University of Freiburg, Germany（弗赖堡大学计算机科学系）

专题命中机器人学习：robot policy(title)；manipulation(abstract)；分类 cs.RO、cs.AI、cs.LG；robotics(comments)

AI总结提出MiDiGap方法，利用少量演示和相机观测，通过离散时间高斯过程混合实现机器人操作策略的灵活表示与模仿学习，在长时域、高约束、动态和多模态任务上取得SOTA性能，并支持推理时引导。

Comments Submitted for publication to IEEE Transaction on Robotics

2409.02337 2024-09-24 cs.RO cs.AI cs.CV 83%

Coaching a Robotic Sonographer: Learning Robotic Ultrasound with Sparse Expert's Feedback

Deepak Raina, Mythra V. Balakuntala, Byung Wook Kim, Juan Wachs, Richard Voyles

专题命中机器人学习：robotic(title,abstract)；分类 cs.RO、cs.AI、cs.CV；robotics(comments)

Comments Accepted in IEEE Transactions on Medical Robotics and Bionics (TMRB) 2024

2306.10007 2023-12-15 cs.RO cs.CV cs.LG 83%

Robot Learning with Sensorimotor Pre-training

Ilija Radosavovic, Baifeng Shi, Letian Fu, Ken Goldberg, Trevor Darrell, Jitendra Malik

专题命中机器人学习：robot learning(title)；robotics(abstract)；分类 cs.RO、cs.CV、cs.LG；robotic(comments)

Comments CoRL 2023; Project page: https://robotic-pretrained-transformer.github.io

2110.05702 2021-10-13 cs.RO cs.AI cs.LG 83%

Auditing Robot Learning for Safety and Compliance during Deployment

Homanga Bharadhwaj

专题命中机器人学习：robot learning(title,abstract)；分类 cs.RO、cs.AI、cs.LG

Comments Blue Sky paper at the 5th Conference on Robot Learning (CoRL 2021)

1905.04218 2019-05-13 cs.RO cs.AI cs.HC cs.LG 83%

Quantifying Teaching Behaviour in Robot Learning from Demonstration

Aran Sena, Matthew J Howard

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

Comments Preprint for International Journal of Robotics Research (IJRR) submission

1810.07167 2018-10-17 cs.RO cs.AI cs.LG 83%

Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation

Gregory Kahn, Adam Villaflor, Pieter Abbeel, Sergey Levine

专题命中机器人学习：navigation(title)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG；robot learning(comments)

Comments Accepted to the Conference on Robot Learning (CoRL) 2018. Video at https://youtu.be/lOLT7zifEkg

2511.06667 2026-07-09 cs.RO cs.AI 版本更新 82%

Rapidly Learning Soft Robot Control via Implicit Time-Stepping

通过隐式时间步长快速学习软机器人控制

Andrew Choi, Dezhong Tong, Xiaonan Huang

机构 * Horizon Robotics ； University of Michigan（密歇根大学）

专题命中机器人学习：robotics(abstract)；robot learning(abstract)；robot policy(abstract)；robotic(abstract)

AI总结研究针对软机器人模拟框架稀缺及策略学习难的问题，采用隐式时间步长，以DisMech模拟器及增量自然曲率控制方法，经与Elastica对比实验，证明该方法能在不牺牲准确性的情况下显著加速软机器人策略学习。

Comments Accepted to IROS 2026. Code: https://github.com/QuantuMope/dismech-rl

2601.16163 2026-01-23 cs.AI cs.RO 82%

Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning

Cosmos Policy: 为视觉运动控制和规划微调视频模型

Moo Jin Kim, Yihuai Gao, Tsung-Yi Lin, Yen-Chen Lin, Yunhao Ge, Grace Lam, Percy Liang, Shuran Song, Ming-Yu Liu, Chelsea Finn, Jinwei Gu

机构 * NVIDIA ； Stanford University（斯坦福大学）

专题命中机器人学习：robotics(abstract)；manipulation(abstract)；world model(abstract)；robot policy(abstract)

AI总结 Cosmos Policy通过单阶段后训练将预训练视频模型转化为高效机器人策略，实现视觉运动控制与规划的先进性能。

2509.19571 2025-09-25 cs.RO cs.CV 82%

Agentic Scene Policies: Unifying Space, Semantics, and Affordances for Robot Action

Sacha Morin, Kumaraditya Gupta, Mahtab Sandhu, Charlie Gauthier, Francesco Argenziano, Kirsty Ellis, Liam Paull

机构 * Université de Montréal（蒙特利尔大学）； Mila - Quebec AI Institute（魁北克人工智能研究院）； Sapienza University of Rome（罗马萨皮恩扎大学）

专题命中机器人学习：robotics(abstract)；manipulation(abstract)；navigation(abstract)；robot policy(abstract)

Comments Project page: https://montrealrobotics.ca/agentic-scene-policies.github.io/

2010.08669 2021-02-26 cs.RO cs.LG 82%

Robot Learning with Crash Constraints

Alonso Marco, Dominik Baumann, Majid Khadiv, Philipp Hennig, Ludovic Righetti, Sebastian Trimpe

专题命中机器人学习：robot learning(title)；robotic(abstract)；robotics(comments,journal_ref)；分类 cs.RO、cs.LG

Comments 8 pages, 4 figures, 1 table, 1 algorithm. Accepted for publication in IEEE Robotics and Automation Letters (RA-L). Video demonstration of the experiments available at https://youtu.be/RAiIo0l6_rE . Algorithm implementation available at https://github.com/alonrot/classified_regression.git

Journal ref IEEE Robotics and Automation Letters, Vol 6(2), pp. 1439-1446, 2021

2505.04999 2026-07-31 cs.RO cs.AI cs.LG 版本更新 82%

CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations

CLAM：基于未标记演示的连续潜在动作模型用于机器人学习

Anthony Liang, Pavel Czempin, Matthew M. Hong, Yutai Zhou, Jingzhen Wang, Erdem Biyik, Stephen Tu

机构 * Department of Computer Science, University of Southern California（南加州大学计算机科学系）； Department of Electrical and Computer Engineering, University of Southern California（南加州大学电气与计算机工程系）

专题命中机器人学习：robot learning(title)；manipulation(abstract)；分类 cs.RO、cs.AI、cs.LG

AI总结 CLAM通过连续潜在动作标签和联合训练动作解码器，有效解决复杂连续控制任务中未标记数据的学习问题，实现在DMControl和MetaWorld等基准及真实机器人上的性能提升。

Comments Latent Action Models, Self-supervised Pretraining, Learning from Videos

Journal ref IEEE/RSJ International Conference on Intelligent Robots and Systems 2026

2606.21139 2026-06-23 cs.RO cs.AI cs.LG 新提交 82%

PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning

PoLAR：分解潜在动作中的程度和模式用于机器人策略学习

Youngjoon Jeong, Jihwan Yu, Minsoo Jo, Junha Chun, Taesup Kim

机构 * Seoul National University（首尔国立大学）

专题命中机器人学习：robot policy(title,abstract)；分类 cs.RO、cs.AI、cs.LG

AI总结提出PoLAR方法，通过径向方向结构分解潜在动作中的程度和模式，利用时间偏移作为程度代理，在双曲空间中实现，提升下游策略性能。

Comments Project Page: https://joon-stack.github.io/PoLAR

2603.24350 2026-06-16 cs.RO cs.AI cs.LG 版本更新 82%

Evidence of an Emergent "Self" in Continual Robot Learning

持续机器人学习中涌现的“自我”证据

Adidev Jhunjhunwala, Judah Goldfeder, Hod Lipson

机构 * Creative Machines Lab, Department of Mechanical Engineering, Columbia University（创意机器实验室，机械工程系，哥伦比亚大学）； Creative Machines Lab, Department of Computer Science, Columbia University（创意机器实验室，计算机科学系，哥伦比亚大学）

专题命中机器人学习：robot learning(title)；manipulation(abstract)；分类 cs.RO、cs.AI、cs.LG

AI总结通过比较恒定任务与持续学习下机器人的认知结构，发现持续学习机器人形成显著更稳定的不变子网络，该子网络对适应性至关重要，为量化智能系统自我概念提供原则性方法。

Comments 44 pages, 24 figures, includes supplementary materials

2503.12993 2025-03-18 cs.RO cs.AI cs.LG 82%

Robot Policy Transfer with Online Demonstrations: An Active Reinforcement Learning Approach

Muhan Hou, Koen Hindriks, A. E. Eiben, Kim Baraka

专题命中机器人学习：robot policy(title)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

2407.02466 2025-02-25 cs.LG cs.AI cs.RO 82%

PWM: Policy Learning with Multi-Task World Models

Ignat Georgiev, Varun Giridhar, Nicklas Hansen, Animesh Garg

专题命中机器人学习：world model(title,abstract)；分类 cs.RO、cs.AI、cs.LG

Comments Visualizations and code available at https://www.imgeorgiev.com/pwm

2401.11439 2024-09-24 cs.RO cs.AI cs.CV 82%

General Flow as Foundation Affordance for Scalable Robot Learning

Chengbo Yuan, Chuan Wen, Tong Zhang, Yang Gao

专题命中机器人学习：robot learning(title)；manipulation(abstract)；分类 cs.RO、cs.AI、cs.CV

Comments https://general-flow.github.io

2312.10069 2023-12-19 cs.RO cs.CV cs.LG 82%

Understanding Representations Pretrained with Auxiliary Losses for Embodied Agent Planning

Yuxuan Li, Luca Weihs

专题命中机器人学习：embodied agent(title)；embodied AI(abstract)；分类 cs.RO、cs.CV、cs.LG

2309.04974 2023-09-19 cs.RO cs.AI cs.LG 82%

Continual Robot Learning using Self-Supervised Task Inference

Muhammad Burhan Hafez, Stefan Wermter

专题命中机器人学习：robot learning(title,abstract)；分类 cs.RO、cs.AI、cs.LG

Comments Accepted for publication in IEEE Transactions on Cognitive and Developmental Systems

2305.14365 2023-05-25 cs.LG cs.AI cs.RO 82%

Continually Learned Pavlovian Signalling Without Forgetting for Human-in-the-Loop Robotic Control

Adam S. R. Parker, Michael R. Dawson, Patrick M. Pilarski

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

Comments 12 pages inc. supplementary, 7 figures, 3 algorithms, Published the NeurIPS Workshop on Human in the Loop Learning, Nov 28 - Dec 8 2022

2301.08794 2023-01-24 cs.RO cs.AI cs.CV cs.IR cs.SY eess.SY 82%

Robot Skill Learning Via Classical Robotics-Based Generated Datasets: Advantages, Disadvantages, and Future Improvement

Batu Kaan Oezen

专题命中机器人学习：robotics(title,abstract)；分类 cs.RO、cs.AI、cs.CV

2210.09435 2022-10-19 cs.RO cs.AI cs.LG 82%

Robot Learning Theory of Mind through Self-Observation: Exploiting the Intentions-Beliefs Synergy

Francesca Bianco, Dimitri Ognibene

专题命中机器人学习：robot learning(title)；robotics(abstract)；分类 cs.RO、cs.AI、cs.LG

2202.05244 2022-06-22 cs.LG cs.AI cs.RO 82%

REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer

Xingyu Liu, Deepak Pathak, Kris M. Kitani

专题命中机器人学习：robot policy(title)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments ICML 2022 (Long Oral)

2105.04607 2021-06-02 cs.RO cs.AI cs.LG 82%

Efficient Self-Supervised Data Collection for Offline Robot Learning

Shadi Endrawis, Gal Leibovich, Guy Jacob, Gal Novik, Aviv Tamar

专题命中机器人学习：robot learning(title)；manipulation(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments Accepted in ICRA 2021

2103.14633 2021-03-29 cs.RO cs.CV cs.LG cs.NE 82%

Visionary: Vision architecture discovery for robot learning

Iretiayo Akinola, Anelia Angelova, Yao Lu, Yevgen Chebotar, Dmitry Kalashnikov, Jacob Varley, Julian Ibarz, Michael S. Ryoo

专题命中机器人学习：robot learning(title)；manipulation(abstract)；分类 cs.RO、cs.CV、cs.LG

Journal ref ICRA 2021

1. 机器人学习 858 篇

Fast Skill Learning for Variable Compliance Robotic Assembly

Constraint Estimation and Derivative-Free Recovery for Robot Learning from Demonstrations

Collaborative Robot Learning from Demonstrations using Hidden Markov Model State Distribution

Experiential Robot Learning with Accelerated Neuroevolution

Interactive Robot Learning of Gestures, Language and Affordances

A survey of robot learning from demonstrations for Human-Robot Collaboration

The Unreasonable Effectiveness of Discrete-Time Gaussian Process Mixtures for Robot Policy Learning

Coaching a Robotic Sonographer: Learning Robotic Ultrasound with Sparse Expert's Feedback

Robot Learning with Sensorimotor Pre-training

Auditing Robot Learning for Safety and Compliance during Deployment

Quantifying Teaching Behaviour in Robot Learning from Demonstration

Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation

Rapidly Learning Soft Robot Control via Implicit Time-Stepping

Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning

Agentic Scene Policies: Unifying Space, Semantics, and Affordances for Robot Action

Robot Learning with Crash Constraints

CLAM: Continuous Latent Action Models for Robot Learning from Unlabeled Demonstrations

PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning

Evidence of an Emergent "Self" in Continual Robot Learning

Robot Policy Transfer with Online Demonstrations: An Active Reinforcement Learning Approach

PWM: Policy Learning with Multi-Task World Models

General Flow as Foundation Affordance for Scalable Robot Learning

Understanding Representations Pretrained with Auxiliary Losses for Embodied Agent Planning

Continual Robot Learning using Self-Supervised Task Inference

Continually Learned Pavlovian Signalling Without Forgetting for Human-in-the-Loop Robotic Control

Robot Skill Learning Via Classical Robotics-Based Generated Datasets: Advantages, Disadvantages, and Future Improvement

Robot Learning Theory of Mind through Self-Observation: Exploiting the Intentions-Beliefs Synergy

REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer

Efficient Self-Supervised Data Collection for Offline Robot Learning

Visionary: Vision architecture discovery for robot learning