机器人 / 具身智能 - arXivDaily 专题

2412.12237 2024-12-18 cs.RO cs.AI cs.LG 76%

Equivariant Action Sampling for Reinforcement Learning and Planning

Linfeng Zhao, Owen Howell, Xupeng Zhu, Jung Yeon Park, Zhewen Zhang, Robin Walters, Lawson L. S. Wong

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

Comments Published at International Workshop on the Algorithmic Foundations of Robotics (WAFR) 2024. Website: http://lfzhao.com/EquivSampling

2408.14336 2024-08-27 cs.RO cs.AI cs.CV 76%

Equivariant Reinforcement Learning under Partial Observability

Hai Nguyen, Andrea Baisero, David Klee, Dian Wang, Robert Platt, Christopher Amato

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

Comments Conference on Robot Learning, 2023

2407.15403 2024-07-23 cs.RO cs.AI cs.LG 76%

Offline Imitation Learning Through Graph Search and Retrieval

Zhao-Heng Yin, Pieter Abbeel

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

Comments Robotics: Science and Systems (RSS) 2024

2207.07560 2022-12-13 cs.LG cs.AI cs.RO 76%

Skill-based Model-based Reinforcement Learning

Lucy Xiaoyang Shi, Joseph J. Lim, Youngwoon Lee

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

Comments Published at the Conference on Robot Learning (CoRL) 2022. Website: https://clvrai.com/skimo

2212.03363 2022-12-08 cs.RO cs.AI cs.LG 76%

Few-Shot Preference Learning for Human-in-the-Loop RL

Joey Hejna, Dorsa Sadigh

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

Comments 6th Annual Conference on Robot Learning (CoRL) 2022

2103.04909 2022-03-01 cs.LG cs.AI cs.NE cs.RO 76%

Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing

Axel Brunnbauer, Luigi Berducci, Andreas Brandstätter, Mathias Lechner, Ramin Hasani, Daniela Rus, Radu Grosu

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

Comments This paper is accepted for presentation at the International Conference on Robotics and Automation (ICRA), 2022

2111.09884 2021-11-19 cs.RO cs.AI cs.LG 76%

Assisted Robust Reward Design

Jerry Zhi-Yang He, Anca D. Dragan

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

Comments 5th Conference on Robot Learning (CoRL 2021)

2010.15920 2021-05-19 cs.LG cs.AI cs.RO 76%

Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones

Brijen Thananjeyan, Ashwin Balakrishna, Suraj Nair, Michael Luo, Krishnan Srinivasan, Minho Hwang, Joseph E. Gonzalez, Julian Ibarz, Chelsea Finn, Ken Goldberg

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

Comments RA-L and ICRA 2021. First two authors contributed equally

Journal ref Robotics and Automation Letters (RA-L) and International Conference on Robotics and Automation (ICRA) 2021

2005.10872 2020-05-27 cs.RO cs.AI cs.LG cs.SY eess.SY 76%

Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning

Michelle A. Lee, Carlos Florensa, Jonathan Tremblay, Nathan Ratliff, Animesh Garg, Fabio Ramos, Dieter Fox

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

Journal ref International Conference in Robotics and Automation 2020

2004.00716 2020-04-03 cs.RO cs.AI cs.LG 76%

Constrained-Space Optimization and Reinforcement Learning for Complex Tasks

Ya-Yen Tsai, Bo Xiao, Edward Johns, Guang-Zhong Yang

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

Comments Accepted for publication in RA-Letters and at ICRA 2020

Journal ref IEEE Robotics and Automation Letters, 5(2) (2020) 682-689

1911.00238 2019-11-04 cs.LG cs.AI cs.RO 76%

Situated GAIL: Multitask imitation using task-conditioned adversarial inverse reinforcement learning

Kyoichiro Kobayashi, Takato Horii, Ryo Iwaki, Yukie Nagai, Minoru Asada

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

Comments Submitted to Advanced Robotics

1707.05300 2018-07-24 cs.AI cs.LG cs.NE cs.RO 76%

Reverse Curriculum Generation for Reinforcement Learning

Carlos Florensa, David Held, Markus Wulfmeier, Michael Zhang, Pieter Abbeel

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

Comments Published at the 1st Conference on Robot Learning (CoRL 2017)

2509.01838 2026-07-10 cs.LG cs.AI 76%

Goal-Conditioned Reinforcement Learning for Data-Driven Maritime Navigation

面向数据驱动的航海导航的基于目标的强化学习

Vaishnav Vaidheeswaran, Dilith Jayakody, Samruddhi Mulay, Anand Lo, Md Mahbub Alam, Gabriel Spadon

机构 * Faculty of Computer Science（计算机科学学院）

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

AI总结本文提出基于目标的强化学习方法，用于数据驱动的航海导航，通过多离散动作空间学习优化路线，结合动作掩码与正向奖励提升策略性能。

Journal ref IEEE International Conference on Big Data (BigData), 2025, pp. 1194-1203

1803.10371 2026-06-04 cs.RO cs.LG cs.SY eess.SY 76%

Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system

基于非操控操作的强化学习：从仿真到物理系统的迁移

Kendall Lowrey, Svetoslav Kolev, Jeremy Dao, Aravind Rajeswaran, Emanuel Todorov

机构 * University of Washington（华盛顿大学）； Roboti LLC（Roboti公司）

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

AI总结本文提出了一种基于仿真的强化学习方法，用于非操控操作任务，通过在仿真环境中训练策略，成功迁移到物理系统中，且在模型集合训练下提升了策略的鲁棒性。

Comments Accepted at IEEE SIMPAR 2018. Project page: https://sites.google.com/view/phantomsim2real

2406.19741 2026-05-12 cs.RO cs.AI 76%

ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning

ROS-LLM：一个用于具身AI的ROS框架，具有任务反馈和结构化推理

Christopher E. Mower, Yuhui Wan, Hongzhan Yu, Antoine Grosnit, Jonas Gonzalez-Billandon, Matthieu Zimmer, Jinlong Wang, Xinyu Zhang, Yao Zhao, Anbang Zhai, Puze Liu, Daniel Palenicek, Davide Tateo, Cesar Cadena, Marco Hutter, Jan Peters, Guangjian Tian, Yuzheng Zhuang, Kun Shao, Xingyue Quan, Jianye Hao, Jun Wang, Haitham Bou-Ammar

机构 * Huawei Noah’s Ark Lab（华为诺亚实验室）； University of Leeds（利兹大学）； Technical University of Darmstadt（达姆施塔特技术大学）； East China Normal University（华东师范大学）； Huawei Technologies（华为技术有限公司）； ETH Zurich（苏黎世联邦理工学院）； University College London（伦敦大学学院）

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

AI总结本文提出一种基于ROS的框架，允许非专家通过自然语言提示和上下文信息编程机器人，结合大语言模型实现任务描述和行为模式控制，实验验证了其在多样化场景中的鲁棒性和扩展性。

Comments This document contains 26 pages and 13 figures

Journal ref Nature Machine Intelligence 8, 313-325 (2026)

2604.02686 2026-04-06 cs.LG cs.AI 76%

Beyond Semantic Manipulation: Token-Space Attacks on Reward Models

超越语义操控：奖励模型中的标记空间攻击

Yuheng Zhang, Mingyue Huo, Minghao Zhu, Mengxue Zhang, Nan Jiang

机构 * UIUC（伊利诺伊大学厄巴纳-香槟分校）； Independent Researcher（独立研究员）； University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）

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

AI总结本文提出Token Mapping Perturbation Attack（TOMPA）框架，通过在标记空间中进行对抗优化，发现非语言标记模式以提升奖励模型性能，揭示了当前RLHF流程的关键漏洞。

2509.13386 2026-03-09 cs.RO cs.LG 76%

VEGA: Electric Vehicle Navigation Agent via Physics-Informed Neural Operator and Proximal Policy Optimization

VEGA：基于物理信息神经算子和近端策略优化的电动汽车导航代理

Hansol Lim, Minhyeok Im, Jonathan Boyack, Jee Won Lee, Jongseong Brad Choi

机构 * Department of Mechanical Engineering, State University of New York（机械工程系，纽约州立大学）； Department of Computer Science, State University of New York（计算机科学系，纽约州立大学）

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

AI总结 VEGA通过结合物理信息神经算子和近端策略优化，为电动汽车提供高效的能耗感知导航方案，实现快速路径规划和充电站点选择。

Comments This work has been submitted to the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) for possible publication

2406.03862 2026-02-18 cs.LG cs.AI 76%

Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation

对抗性行为操控下的鲁棒深度强化学习

Shojiro Yamabe, Kazuto Fukuchi, Jun Sakuma

机构 * Institute of Science Tokyo（东京科学研究所）； University of Tsukuba（筑波大学）； RIKEN AIP（理化学研究所AIP）

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

AI总结本文提出了一种基于模仿学习的对抗性攻击方法，并通过时间折扣正则化提升强化学习对行为定向攻击的鲁棒性。

Comments Accepted at ICLR 2026

2602.12492 2026-02-16 cs.RO cs.LG 76%

Composable Model-Free RL for Navigation with Input-Affine Systems

可组合的无模型强化学习用于具有输入仿射系统的导航

Xinhuan Sang, Abdelrahman Abdelgawad, Roberto Tron

机构 * Boston University（波士顿大学）

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

AI总结本文提出了一种可组合的无模型强化学习方法，用于具有输入仿射系统的导航，通过在线组合学习的价值函数和策略实现目标到达和碰撞避免。

Comments 17 pages, 8 figures. Submitted to WAFR 2026 (under review)

2505.00540 2026-01-21 cs.MA cs.LG cs.RO cs.SY eess.SY 76%

Emergence of Roles in Robotic Teams with Model Sharing and Limited Communication

机器人团队中角色涌现：模型共享与有限通信

Ian O'Flynn, Harun Šiljak

机构 * EEE Department（电子工程系）； Trinity College Dublin（都柏林信任学院）

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

AI总结通过集中学习和模型共享，该方法在机器人团队中促进角色分化，减少计算能耗并应用于现实场景。

Comments Accepted for 2025 8th International Balkan Conference on Communications and Networking (Balkancom)

2509.21045 2025-09-26 cs.RO cs.LG 76%

MPC-based Deep Reinforcement Learning Method for Space Robotic Control with Fuel Sloshing Mitigation

Mahya Ramezani, M. Amin Alandihallaj, Barış Can Yalçın, Miguel Angel Olivares Mendez, Holger Voos

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

Comments Pre-print version submitted to IEEE IROS

2503.08872 2025-03-13 cs.LG cs.AI cs.OS 76%

Meta-Reinforcement Learning with Discrete World Models for Adaptive Load Balancing

Cameron Redovian

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

Comments 6 pages, 1 figure, to be published in ACMSE 2025

1809.08835 2024-10-30 cs.RO cs.LG 76%

Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning

Changan Chen, Yuejiang Liu, Sven Kreiss, Alexandre Alahi

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

Comments Accepted at ICRA2019

2311.07822 2024-10-01 cs.RO cs.AI 76%

A Central Motor System Inspired Pre-training Reinforcement Learning for Robotic Control

Pei Zhang, Zhaobo Hua, Jinliang Ding

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

Comments 12 pages; 9 figures

2403.12014 2024-07-15 cs.CL cs.AI cs.LG 76%

EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents

Abhay Zala, Jaemin Cho, Han Lin, Jaehong Yoon, Mohit Bansal

专题命中模仿学习与强化学习：embodied agent(title)；分类 cs.AI、cs.LG

Comments COLM 2024; First two authors contributed equally; Project website: https://envgen-llm.github.io/

2406.07381 2024-06-12 cs.AI cs.LG 76%

World Models with Hints of Large Language Models for Goal Achieving

Zeyuan Liu, Ziyu Huan, Xiyao Wang, Jiafei Lyu, Jian Tao, Xiu Li, Furong Huang, Huazhe Xu

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

2401.08381 2024-06-04 cs.RO cs.LG 76%

Robotic Imitation of Human Actions

Josua Spisak, Matthias Kerzel, Stefan Wermter

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

Comments Accepted at the ICDL 2024

2309.13285 2024-05-07 cs.RO cs.AI cs.MA 76%

Collision Avoidance and Navigation for a Quadrotor Swarm Using End-to-end Deep Reinforcement Learning

Zhehui Huang, Zhaojing Yang, Rahul Krupani, Baskın Şenbaşlar, Sumeet Batra, Gaurav S. Sukhatme

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

Comments Accepted to ICRA 2024

2404.09927 2024-04-16 cs.RO cs.LG 76%

Autonomous Path Planning for Intercostal Robotic Ultrasound Imaging Using Reinforcement Learning

Yuan Bi, Cheng Qian, Zhicheng Zhang, Nassir Navab, Zhongliang Jiang

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

2403.18219 2024-03-28 cs.LG cs.AI stat.CO 76%

From Two-Dimensional to Three-Dimensional Environment with Q-Learning: Modeling Autonomous Navigation with Reinforcement Learning and no Libraries

Ergon Cugler de Moraes Silva

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

1. 模仿学习与强化学习 4111 篇

Equivariant Action Sampling for Reinforcement Learning and Planning

Equivariant Reinforcement Learning under Partial Observability

Offline Imitation Learning Through Graph Search and Retrieval

Skill-based Model-based Reinforcement Learning

Few-Shot Preference Learning for Human-in-the-Loop RL

Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing

Assisted Robust Reward Design

Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones

Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning

Constrained-Space Optimization and Reinforcement Learning for Complex Tasks

Situated GAIL: Multitask imitation using task-conditioned adversarial inverse reinforcement learning

Reverse Curriculum Generation for Reinforcement Learning

Goal-Conditioned Reinforcement Learning for Data-Driven Maritime Navigation

Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system

ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning

Beyond Semantic Manipulation: Token-Space Attacks on Reward Models

VEGA: Electric Vehicle Navigation Agent via Physics-Informed Neural Operator and Proximal Policy Optimization

Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation

Composable Model-Free RL for Navigation with Input-Affine Systems

Emergence of Roles in Robotic Teams with Model Sharing and Limited Communication

MPC-based Deep Reinforcement Learning Method for Space Robotic Control with Fuel Sloshing Mitigation

Meta-Reinforcement Learning with Discrete World Models for Adaptive Load Balancing

Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning

A Central Motor System Inspired Pre-training Reinforcement Learning for Robotic Control

EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents

World Models with Hints of Large Language Models for Goal Achieving

Robotic Imitation of Human Actions

Collision Avoidance and Navigation for a Quadrotor Swarm Using End-to-end Deep Reinforcement Learning

Autonomous Path Planning for Intercostal Robotic Ultrasound Imaging Using Reinforcement Learning

From Two-Dimensional to Three-Dimensional Environment with Q-Learning: Modeling Autonomous Navigation with Reinforcement Learning and no Libraries