机器人 / 具身智能 - arXivDaily 专题

2204.03516 2022-04-08 cs.RO cs.AI cs.LG cs.MA 69%

Distributed Reinforcement Learning for Robot Teams: A Review

Yutong Wang, Mehul Damani, Pamela Wang, Yuhong Cao, Guillaume Sartoretti

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.RO、cs.AI、cs.LG；robotics(comments)

Comments Preprint of the paper submitted to Springer's Current Robotics Reports

2109.01115 2021-11-02 cs.RO cs.AI cs.LG 69%

Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation

Suraj Nair, Eric Mitchell, Kevin Chen, Brian Ichter, Silvio Savarese, Chelsea Finn

专题命中模仿学习与强化学习：manipulation(abstract)；分类 cs.RO、cs.AI、cs.LG；robot learning(comments)

Comments Conference on Robot Learning (CoRL) 2021. 24 Pages, 18 Figures

2109.12750 2021-10-20 cs.LG cs.AI cs.RO 69%

Learning Multimodal Rewards from Rankings

Vivek Myers, Erdem Bıyık, Nima Anari, Dorsa Sadigh

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.RO、cs.AI、cs.LG；robot learning(comments)

Comments 17 pages, 12 figures, 2 tables. Published at Conference on Robot Learning (CoRL) 2021

1909.07876 2020-08-10 cs.RO cs.AI cs.LG 69%

Learning to Manipulate Object Collections Using Grounded State Representations

Matthew Wilson, Tucker Hermans

专题命中模仿学习与强化学习：robot learning(abstract,comments)；分类 cs.RO、cs.AI、cs.LG

Comments Accepted to Conference on Robot Learning 2019 (Oral); Video results: https://bit.ly/2khSKUs; v3: fix abstract and appendix

1912.04443 2020-06-23 cs.RO cs.CV cs.LG 69%

AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos

Laura Smith, Nikita Dhawan, Marvin Zhang, Pieter Abbeel, Sergey Levine

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.RO、cs.CV、cs.LG；robotics(comments)

Comments Robotics: Science and Systems (RSS) 2020 camera ready submission. Project website: https://sites.google.com/view/rss20avid

2005.02575 2020-06-05 cs.RO cs.AI cs.LG 69%

Active Preference-Based Gaussian Process Regression for Reward Learning

Erdem Bıyık, Nicolas Huynh, Mykel J. Kochenderfer, Dorsa Sadigh

专题命中模仿学习与强化学习：robotics(abstract,comments)；分类 cs.RO、cs.AI、cs.LG

Comments Proceedings of Robotics: Science and Systems (RSS), July 2020

1906.11228 2020-05-20 cs.LG cs.AI cs.RO stat.ML 69%

Compositional Transfer in Hierarchical Reinforcement Learning

Markus Wulfmeier, Abbas Abdolmaleki, Roland Hafner, Jost Tobias Springenberg, Michael Neunert, Tim Hertweck, Thomas Lampe, Noah Siegel, Nicolas Heess, Martin Riedmiller

专题命中模仿学习与强化学习：robotics(abstract,comments)；分类 cs.RO、cs.AI、cs.LG

Comments Robotics Science and Systems 2020

1910.12908 2020-03-10 cs.RO cs.AI cs.LG 69%

Certified Adversarial Robustness for Deep Reinforcement Learning

Björn Lütjens, Michael Everett, Jonathan P. How

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.RO、cs.AI、cs.LG；robot learning(comments)

Comments Published at Conference on Robot Learning (CoRL) 2019; (v2) contains minor updates to related works; (v3) acknowledged AWS

Journal ref Proceedings of Machine Learning Research (PMLR) Vol. 100, 2019

1911.11744 2019-11-27 cs.RO cs.CL cs.CV cs.LG 69%

Imitation Learning of Robot Policies by Combining Language, Vision and Demonstration

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

专题命中模仿学习与强化学习：robot policy(abstract)；分类 cs.RO、cs.CV、cs.LG；robot learning(comments)

Comments Accepted to the NeurIPS 2019 Workshop on Robot Learning: Control and Interaction in the Real World, Vancouver, Canada

1908.05256 2019-08-15 cs.RO cs.AI cs.LG cs.SY eess.SY 69%

Continuous Control for High-Dimensional State Spaces: An Interactive Learning Approach

Rodrigo Pérez-Dattari, Carlos Celemin, Javier Ruiz-del-Solar, Jens Kober

专题命中模仿学习与强化学习：robotics(abstract,comments)；分类 cs.RO、cs.AI、cs.LG

Comments 7 pages, 8 figures, IEEE International Conference on Robotics and Automation (ICRA 2019)

1905.12197 2019-05-30 cs.RO cs.AI cs.LG 69%

LeTS-Drive: Driving in a Crowd by Learning from Tree Search

Panpan Cai, Yuanfu Luo, Aseem Saxena, David Hsu, Wee Sun Lee

专题命中模仿学习与强化学习：robotics(abstract,journal_ref)；分类 cs.RO、cs.AI、cs.LG

Journal ref Proc. Robotics: Science & Systems (RSS), 2019

1610.00673 2019-05-29 cs.LG cs.AI cs.RO 69%

Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search

Ali Yahya, Adrian Li, Mrinal Kalakrishnan, Yevgen Chebotar, Sergey Levine

专题命中模仿学习与强化学习：manipulation(abstract)；分类 cs.RO、cs.AI、cs.LG；robotics(comments)

Comments Submitted to the IEEE International Conference on Robotics and Automation 2017

1811.08067 2019-02-19 cs.RO cs.CV cs.LG 69%

Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions

Ricson Cheng, Arpit Agarwal, Katerina Fragkiadaki

专题命中模仿学习与强化学习：manipulation(abstract)；分类 cs.RO、cs.CV、cs.LG；robot learning(comments)

Comments The paper was present in Conference of Robot Learning 2018

Journal ref Proceedings of Machine Learning Research 87 (2018) 422--431

1810.04303 2018-10-11 cs.LG cs.AI cs.RO stat.ML 69%

Batch Active Preference-Based Learning of Reward Functions

Erdem Bıyık, Dorsa Sadigh

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.RO、cs.AI、cs.LG；robot learning(comments)

Comments Proceedings of the 2nd Conference on Robot Learning (CoRL), October 2018

1710.02410 2018-03-05 cs.RO cs.CV cs.LG 69%

End-to-end Driving via Conditional Imitation Learning

Felipe Codevilla, Matthias Müller, Antonio López, Vladlen Koltun, Alexey Dosovitskiy

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.RO、cs.CV、cs.LG；robotics(comments)

Comments Published at the International Conference on Robotics and Automation (ICRA), 2018

1307.0813 2014-02-13 stat.ML cs.AI cs.LG cs.RO 69%

Multi-Task Policy Search

Marc Peter Deisenroth, Peter Englert, Jan Peters, Dieter Fox

专题命中模仿学习与强化学习：robotics(abstract,comments)；分类 cs.RO、cs.AI、cs.LG

Comments 8 pages, double column. IEEE International Conference on Robotics and Automation, 2014

2512.03729 2026-04-01 cs.RO cs.LG cs.SY eess.SY 68%

Autonomous Planning In-space Assembly Reinforcement-learning free-flYer (APIARY) International Space Station Astrobee Testing

自主空间组装强化学习自由飞行器（APIARY）国际空间站Astrobee测试

Samantha Chapin, Kenneth Stewart, Roxana Leontie, Carl Glen Henshaw

机构 * U.S. Naval Research Laboratory Naval Center for Space Technology（美国海军研究实验室海军空间技术中心）

专题命中模仿学习与强化学习：robotic(abstract)；robotics(comments,journal_ref)；分类 cs.RO、cs.LG

AI总结 APIARY实验利用强化学习控制空间自由飞行器，通过NASA Astrobee机器人在国际空间站进行首次空间强化学习控制测试，验证了强化学习在提升机器人自主性方面的潜力。

Comments iSpaRo 2025, Best Paper Award in Orbital Robotics

Journal ref 2025 International Conference on Space Robotics (iSpaRo)

2403.10996 2026-02-24 cs.RO cs.LG cs.MA 68%

Mixed-Reality Digital Twins: Leveraging the Physical and Virtual Worlds for Hybrid Sim2Real Transition of Multi-Agent Reinforcement Learning Policies

混合现实数字孪生：利用物理与虚拟世界实现多智能体强化学习策略的混合仿真到现实过渡

Chinmay Vilas Samak, Tanmay Vilas Samak, Venkat Narayan Krovi

机构 * Department of Automotive Engineering, Clemson University International Center for Automotive Research (CU-ICAR)（汽车工程系，克莱姆森大学国际汽车研究中心（CU-ICAR））

专题命中模仿学习与强化学习：embodied agent(abstract)；robotics(comments,journal_ref)；分类 cs.RO、cs.LG

AI总结本文提出混合现实数字孪生框架，通过并行化和域随机化技术，显著提升多智能体强化学习策略的训练效率和仿真到现实迁移性能。

Comments Accepted in IEEE Robotics and Automation Letters (RA-L) and additionally accepted to be presented at IEEE International Conference on Robotics and Automation (ICRA) 2026

Journal ref IEEE Robotics and Automation Letters, vol. 10, no. 9, pp. 9040-9047, Sept. 2025

2502.06440 2025-11-20 cs.RO cs.AI cs.MA 68%

SIGMA: Sheaf-Informed Geometric Multi-Agent Pathfinding

Shuhao Liao, Weihang Xia, Yuhong Cao, Weiheng Dai, Chengyang He, Wenjun Wu, Guillaume Sartoretti

机构 * Hangzhou International Innovation Institute, Beihang University, China（北京航空航天大学杭州国际创新研究院）； CoreControl Inc, Hangzhou, China（杭州核心控制公司）； Department of Mechanical Engineering, National University of Singapore, Singapore（新加坡国立大学机械工程系）

专题命中模仿学习与强化学习：robotic(abstract)；robotics(comments,journal_ref)；分类 cs.RO、cs.AI

Comments Accepted for presentation at the 2025 IEEE International Conference on Robotics and Automation (ICRA)

Journal ref 2025 IEEE International Conference on Robotics and Automation ICRA pp. 1-7

2203.03432 2023-02-07 cs.RO cs.LG 68%

Learning Solution Manifolds for Control Problems via Energy Minimization

Miguel Zamora, Roi Poranne, Stelian Coros

专题命中模仿学习与强化学习：robotic(abstract)；robotics(comments,journal_ref)；分类 cs.RO、cs.LG

Comments IEEE Robotics and Automation Letters (RA-L), 2022. Also in: Intelligent Robots and Systems (IROS)

Journal ref IEEE Robotics and Automation Letters, Volume: 7, Issue: 3, p. 7912 - 7919, July 2022

2302.01193 2023-02-03 cs.LG cs.RO 68%

Imitating careful experts to avoid catastrophic events

Jack R. P. Hanslope, Laurence Aitchison

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.RO、cs.LG；robotics(comments)；robot learning(comments)

Comments 9 pages, 8 figures, accepted to NeurIPS 2022 Workshop on Robot Learning: Trustworthy Robotics

1907.02140 2023-01-18 cs.LG cs.AI stat.ML 68%

Integration of Imitation Learning using GAIL and Reinforcement Learning using Task-achievement Rewards via Probabilistic Graphical Model

Akira Kinose, Tadahiro Taniguchi

专题命中模仿学习与强化学习：robotics(abstract,comments)；分类 cs.AI、cs.LG

Comments Submitted to Advanced Robotics

Journal ref Advanced Robotics, 2020, 34:16, 1055-1067

2008.08157 2022-07-12 cs.RO cs.LG cs.SY eess.SY 68%

Heteroscedastic Uncertainty for Robust Generative Latent Dynamics

Oliver Limoyo, Bryan Chan, Filip Marić, Brandon Wagstaff, Rupam Mahmood, Jonathan Kelly

专题命中模仿学习与强化学习：robotic(abstract)；robotics(comments,journal_ref)；分类 cs.RO、cs.LG

Comments In IEEE Robotics and Automation Letters (RA-L) and presented at the IEEE International Conference on Intelligent Robots and Systems (IROS'20), Las Vegas, USA, October 25-29, 2020

Journal ref IEEE Robotics and Automation Letters (RA-L), Vol. 5, No. 4, pp. 6654-6661, Oct. 2020

2605.04568 2026-08-07 cs.LG cs.AI cs.RO 版本更新 67%

Dream-MPC: Gradient-Based Model Predictive Control with Latent Imagination

Dream-MPC：基于梯度与潜在想象的模型预测控制

Jonathan Spieler, Sven Behnke

机构 * Autonomous Intelligent Systems, Computer Science Institute VI - Intelligent Systems（自主智能系统，计算机科学研究所VI - 智能系统）； Robotics, Center for Robotics（机器人学，机器人中心）； the Lamarr Institute for Machine Learning（拉马尔机器学习研究所）； Artificial Intelligence, University of Bonn, Germany（人工智能，波恩大学，德国）

专题命中模仿学习与强化学习：world model(abstract)；分类 cs.RO、cs.AI、cs.LG

AI总结提出Dream-MPC方法，通过从展开策略生成少量候选轨迹，并利用学习的世界模型进行梯度上升优化，结合不确定性正则化和时间上的优化迭代摊销，显著提升了底层策略性能，在24个连续控制任务上优于无梯度MPC和现有基线。

Comments Accepted for International Conference on Machine Learning (ICML) 2026

2607.28737 2026-08-03 cs.LG cs.CV cs.RO 新提交 67%

Mirror Learning

镜像学习

Yunpeng Liu, Matthew Niedoba, Oluwanifemi A. Adekanye, Jason Yoo, Yingchen He, Berend Zwartsenberg, Frank Wood

机构 * University of British Columbia（不列颠哥伦比亚大学）； Inverted AI ； Amii

专题命中模仿学习与强化学习：world model(abstract)；分类 cs.RO、cs.CV、cs.LG

AI总结该研究提出镜像学习框架，通过视频扩散模型的视角变换与逆动力学模型合成镜像数据，用其增强行为克隆训练可提升策略性能，为数据收集提供替代方案。

2506.04147 2026-07-20 cs.RO cs.AI cs.LG 版本更新 67%

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

SLAC：通过无监督模拟预训练实现安全高效的真实机器人强化学习

Jiaheng Hu, Peter Stone, Roberto Martín-Martín

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校）； Sony AI（索尼人工智能）； Amazon Robotics（亚马逊机器人技术）

专题命中模仿学习与强化学习：manipulation(abstract)；分类 cs.RO、cs.AI、cs.LG

AI总结研究旨在解决高自由度机器人强化学习难题，提出SLAC方法，利用低保真模拟器预训练潜在动作空间，通过定制无监督方法训练并用于新型离策略算法，在双手移动操纵任务中达领先性能，高效学习复杂任务。

Comments Preliminary version at CoRL 2025

2607.05391 2026-07-08 cs.AI cs.CL cs.LG cs.MA cs.RO 新提交 67%

LLM-as-a-Verifier: A General-Purpose Verification Framework

LLM-as-a-Verifier：一种通用验证框架

Jacky Kwok, Shulu Li, Pranav Atreya, Yuejiang Liu, Yixing Jiang, Chelsea Finn, Marco Pavone, Ion Stoica, Azalia Mirhoseini

机构 * Stanford University（斯坦福大学）； UC Berkeley（加州大学伯克利分校）； NVIDIA Research（英伟达研究院）

专题命中模仿学习与强化学习：robotics(abstract)；分类 cs.RO、cs.AI、cs.LG

AI总结该工作将验证确定方案正确性的能力作为大模型新扩展轴，提出无需额外训练的通用LLM验证框架，生成连续评分，在多基准上取得SOTA性能，还可用于强化学习等场景。

Comments Code: https://github.com/llm-as-a-verifier/llm-as-a-verifier Website: https://llm-as-a-verifier.com

2407.15283 2026-07-02 cs.LG cs.AI cs.RO 版本更新 67%

Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms

通过强化学习策略梯度算法增强机器的硬件容错能力

Sheila Schoepp, Mehran Taghian, Shotaro Miwa, Yoshihiro Mitsuka, Shadan Golestan, Osmar Zaïane

机构 * Department of Computing Science, University of Alberta（阿尔伯塔大学计算机科学系）； Alberta Machine Intelligence Institute（阿尔伯塔机器智能研究所）； Advanced Technology R&D Center, Mitsubishi Electric Corporation（三菱电机株式会社先进技术研发中心）； Information Technology R&D Center, Mitsubishi Electric Corporation（三菱电机株式会社信息技术研发中心）

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

AI总结本文首次系统比较PPO和SAC两种强化学习算法在硬件故障容错中的表现，并研究四种知识迁移策略，实验表明算法能快速恢复故障并存在性能权衡。

2606.27766 2026-06-29 cs.LG cs.AI cs.RO 新提交 67%

RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance

RS-Diffuser: 基于分布价值引导的风险敏感扩散规划

Shiqiang Gong

机构 * Northwestern Polytechnical University（西北工业大学）

专题命中模仿学习与强化学习：navigation(abstract)；分类 cs.RO、cs.AI、cs.LG

AI总结提出RS-Diffuser，一种结合扩散轨迹生成与分布价值评论家的风险敏感离线规划框架，通过尾部感知目标引导去噪过程，实现灵活的风险偏好行为，在风险敏感D4RL和机器人导航基准上达到最优性能。

Comments ICIC 2026 Oral

2606.19632 2026-06-19 cs.RO cs.AI cs.LG cs.LO cs.MA 新提交 67%

Formal Verification of Learned Multi-Agent Communication Policies via Decision Tree Distillation

通过决策树蒸馏对学习到的多智能体通信策略进行形式化验证

Ahmad Farooq, Kamran Iqbal

机构 * University of Arkansas at Little Rock（阿肯色大学小石城分校）

专题命中模仿学习与强化学习：robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

AI总结提出通过决策树蒸馏将多智能体强化学习策略转化为可解释模型，并利用PRISM进行形式化验证，确保安全属性转移至原始网络，在无人机编队任务中实现88.9%属性满足率。

Comments 9 pages, 3 figures, 7 tables. Accepted at the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2026), Pittsburgh, Pennsylvania, USA, September 27-October 1, 2026

1. 模仿学习与强化学习 4113 篇

Distributed Reinforcement Learning for Robot Teams: A Review

Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation

Learning Multimodal Rewards from Rankings

Learning to Manipulate Object Collections Using Grounded State Representations

AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos

Active Preference-Based Gaussian Process Regression for Reward Learning

Compositional Transfer in Hierarchical Reinforcement Learning

Certified Adversarial Robustness for Deep Reinforcement Learning

Imitation Learning of Robot Policies by Combining Language, Vision and Demonstration

Continuous Control for High-Dimensional State Spaces: An Interactive Learning Approach

LeTS-Drive: Driving in a Crowd by Learning from Tree Search

Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search

Reinforcement Learning of Active Vision for Manipulating Objects under Occlusions

Batch Active Preference-Based Learning of Reward Functions

End-to-end Driving via Conditional Imitation Learning

Multi-Task Policy Search

Autonomous Planning In-space Assembly Reinforcement-learning free-flYer (APIARY) International Space Station Astrobee Testing

Mixed-Reality Digital Twins: Leveraging the Physical and Virtual Worlds for Hybrid Sim2Real Transition of Multi-Agent Reinforcement Learning Policies

SIGMA: Sheaf-Informed Geometric Multi-Agent Pathfinding

Learning Solution Manifolds for Control Problems via Energy Minimization

Imitating careful experts to avoid catastrophic events

Integration of Imitation Learning using GAIL and Reinforcement Learning using Task-achievement Rewards via Probabilistic Graphical Model

Heteroscedastic Uncertainty for Robust Generative Latent Dynamics

Dream-MPC: Gradient-Based Model Predictive Control with Latent Imagination

Mirror Learning

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

LLM-as-a-Verifier: A General-Purpose Verification Framework

Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms

RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance

Formal Verification of Learned Multi-Agent Communication Policies via Decision Tree Distillation