机器人 / 具身智能 - arXivDaily 专题

2301.10528 2023-04-26 cs.RO 61%

An Incremental Inverse Reinforcement Learning Approach for Motion Planning with Separated Path and Velocity Preferences

Armin Avaei, Linda van der Spaa, Luka Peternel, Jens Kober

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

Comments 14 pages, 12 figures, 2 tables, associated video: https://youtu.be/hhL5-Lpzj4M

Journal ref Robotics, 12(2), 61 (2023)

2103.13623 2022-11-08 cs.RO 61%

Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies

Hanbit Oh, Hikaru Sasaki, Brendan Michael, Takamitsu Matsubara

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

Comments 7 pages, Accepted by the 2021 International Conference on Robotics and Automation (ICRA 2021)

2202.00243 2022-07-28 cs.RO cs.AI cs.CV cs.LG cs.SY eess.SY 61%

Adversarial Imitation Learning from Video using a State Observer

Haresh Karnan, Garrett Warnell, Faraz Torabi, Peter Stone

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

Journal ref International Conference on Robotics and Automation (ICRA) 2022

2206.12784 2022-06-28 cs.RO 61%

Learning to Rearrange with Physics-Inspired Risk Awareness

Meng Song, Yuhan Liu, Zhengqin Li, Manmohan Chandraker

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

Comments Accepted to Risk Aware Decision Making Workshop at Robotics, Science and Systems 2022

2204.00898 2022-06-07 cs.RO 61%

Hierarchical Reinforcement Learning under Mixed Observability

Hai Nguyen, Zhihan Yang, Andrea Baisero, Xiao Ma, Robert Platt, Christopher Amato

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

Comments Accepted at the 15th International Workshop on the Algorithmic Foundations of Robotics (WAFR) 2022, University of Maryland, College Park. The first two authors contributed equally

2011.06507 2021-11-08 cs.LG cs.AI cs.CV cs.RO 61%

Reinforcement Learning with Videos: Combining Offline Observations with Interaction

Karl Schmeckpeper, Oleh Rybkin, Kostas Daniilidis, Sergey Levine, Chelsea Finn

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

Journal ref Conference on Robot Learning (2020)

2102.04022 2021-10-20 cs.RO 61%

Towards Hierarchical Task Decomposition using Deep Reinforcement Learning for Pick and Place Subtasks

Luca Marzari, Ameya Pore, Diego Dall'Alba, Gerardo Aragon-Camarasa, Alessandro Farinelli, Paolo Fiorini

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

Comments This work has been accepted to the IEEE International Conference on Advanced Robotics (ICAR) 2021

2106.00534 2021-06-02 cs.RO 61%

DeepWalk: Omnidirectional Bipedal Gait by Deep Reinforcement Learning

Diego Rodriguez, Sven Behnke

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

Comments In: Proceedings of the International Conference on Robotics and Automation (ICRA) 2021

2102.06838 2021-02-16 cs.RO 61%

Learning Variable Impedance Control via Inverse Reinforcement Learning for Force-Related Tasks

Xiang Zhang, Liting Sun, Zhian Kuang, Masayoshi Tomizuka

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

Comments Accepted by IEEE Robotics and Automation Letters. Feb 2020

2008.04460 2020-11-10 cs.RO 61%

Hardware as Policy: Mechanical and Computational Co-Optimization using Deep Reinforcement Learning

Tianjian Chen, Zhanpeng He, Matei Ciocarlie

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

Comments Conference on Robot Learning (CoRL) 2020

1909.11730 2020-08-18 cs.RO cs.AI cs.CV cs.LG 61%

"Good Robot!": Efficient Reinforcement Learning for Multi-Step Visual Tasks with Sim to Real Transfer

Andrew Hundt, Benjamin Killeen, Nicholas Greene, Hongtao Wu, Heeyeon Kwon, Chris Paxton, Gregory D. Hager

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

Comments Accepted to the journal IEEE Robotics and Automation Letters (RA-L) and to be presented at IROS 2020. This is a minor update to v3. 8 pages, 6 figures, 3 tables, 1 algorithm. Code is available at https://github.com/jhu-lcsr/good_robot and a video overview is at https://youtu.be/MbCuEZadkIw

1810.00912 2018-10-03 cs.RO cs.AI cs.CV cs.LG 61%

Visual Curiosity: Learning to Ask Questions to Learn Visual Recognition

Jianwei Yang, Jiasen Lu, Stefan Lee, Dhruv Batra, Devi Parikh

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

Comments 18 pages, 10 figures, Oral Presentation in Conference on Robot Learning (CoRL) 2018

1806.07822 2018-09-20 cs.LG cs.AI cs.CV cs.RO stat.ML 61%

Learning Neural Parsers with Deterministic Differentiable Imitation Learning

Tanmay Shankar, Nicholas Rhinehart, Katharina Muelling, Kris M. Kitani

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

Comments Accepted to Conference on Robot Learning, CoRL 2018

1703.09327 2018-02-01 cs.LG 61%

DART: Noise Injection for Robust Imitation Learning

Michael Laskey, Jonathan Lee, Roy Fox, Anca Dragan, Ken Goldberg

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

Journal ref 1st Conference on Robot Learning (CoRL 2017)

1711.03938 2017-11-13 cs.LG cs.AI cs.CV cs.RO 61%

CARLA: An Open Urban Driving Simulator

Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, Vladlen Koltun

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

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

1709.04905 2017-09-15 cs.LG cs.AI cs.CV cs.RO 61%

One-Shot Visual Imitation Learning via Meta-Learning

Chelsea Finn, Tianhe Yu, Tianhao Zhang, Pieter Abbeel, Sergey Levine

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

Comments Conference on Robot Learning, 2017 (to appear). First two authors contributed equally. Video available at https://sites.google.com/view/one-shot-imitation

1602.04875 2016-02-24 cs.AI 61%

POMDP-lite for Robust Robot Planning under Uncertainty

Min Chen, Emilio Frazzoli, David Hsu, Wee Sun Lee

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

Comments In Proc. IEEE International Conference on Robotics & Automation (ICRA) 2016, with supplementary materials

2511.07403 2026-07-07 cs.CV cs.AI cs.CL cs.LG 版本更新 60%

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

空间思考者：通过密集奖励强化场景图基础的空间推理

Hunar Batra, Haoqin Tu, Hardy Chen, Yuanze Lin, Cihang Xie, Ronald Clark

机构 * University of Oxford（牛津大学）； University of California, Santa Cruz（加州大学圣克鲁兹分校）

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

AI总结研究针对多模态大语言模型空间推理难题，提出SpatialThinker，通过在线强化学习统一场景图生成与视觉推理，构建心理场景图并借助密集奖励推理，贡献包括基于SGG推理、高质量训练数据集及密集奖励设计。

Comments Preprint. Accepted at NeurIPS 2025 Workshops on SPACE in Vision, Language, and Embodied AI (SpaVLE) as Oral, Embodied World Models for Decision Making (EWM), Aligning Reinforcement Learning Experimentalists and Theorists (ARLET), and Scaling Environments for Agents (SEA)

2510.03592 2026-03-17 cs.LG cs.AI cs.MA cs.RO 60%

Deep Reinforcement Learning for Multi-Agent Coordination

多智能体协调的深度强化学习

Kehinde O. Aina, Sehoon Ha

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

AI总结本文提出一种基于信息素的多智能体深度强化学习框架，通过虚拟信息素模拟局部和社会交互，实现无通信的去中心化协调，解决狭窄环境中多机器人协作的挑战。

Comments 11 pages, 8 figures, 1 table, presented at SWARM 2022, to be published in Journal of Artificial Life and Robotics

Journal ref Artificial Life and Robotics (2025)

2503.11433 2025-12-08 cs.RO cs.AI cs.LG cs.SY eess.SY 60%

Adaptive Torque Control of Exoskeletons under Spasticity Conditions via Reinforcement Learning

通过强化学习实现脊髓病变条件下外骨骼的自适应扭矩控制

Andrés Chavarrías, David Rodriguez-Cianca, Pablo Lanillos

机构 * Neuro AI and Robotics Group（神经人工智能与机器人组）； Cajal International Neuroscience Center（卡贾尔国际神经科学中心）； Spanish National Research Council（西班牙国家研究理事会）； Rey Juan Carlos University (URJC)（雷奥恩卡洛斯大学（URJC））

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

AI总结本文提出了一种基于深度强化学习的膝外骨骼自适应扭矩控制器，通过数字双胞胎训练，有效降低痉挛状态下人体关节扭矩和交互力。

Comments Accepted for publication in IEEE 19th International Conference on Rehabilitation Robotics (ICORR2025)

Journal ref International Conference On Rehabilitation Robotics : [Proceedings]. 705-711 - 2025-01-01

2210.16575 2025-07-21 cs.AI cs.LG cs.RO 60%

Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification Algorithms

Resul Dagdanov, Halil Durmus, Nazim Kemal Ure

机构 * ITU Artificial Intelligence and Data Science Research Center（伊斯坦布尔技术大学人工智能与数据科学研究中心）； Department of Aeronautical Engineering（航空工程系）； Eatron Technologies（Eatron技术公司）； Department of Electronics and Communication Engineering（电子与通信工程系）； ITU Artificial Intelligence and Data Science Application and Research Center（伊斯坦布尔技术大学人工智能与数据科学应用与研究中心）； Department of Computer Engineering（计算机工程系）

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

Comments 7 pages, 7 figures, 2 tables, published in IEEE International Conference on Robotics and Automation (ICRA), June 2, 2023, London, UK

Journal ref IEEE International Conference on Robotics and Automation (ICRA), 2023, pp. 5631-5637

2506.04399 2025-06-06 cs.LG cs.AI cs.RO 60%

Unsupervised Meta-Testing with Conditional Neural Processes for Hybrid Meta-Reinforcement Learning

Suzan Ece Ada, Emre Ugur

机构 * Department of Computer Engineering, Bogazici University（计算机工程系，博兹达奇大学）

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

Comments Published in IEEE Robotics and Automation Letters Volume: 9, Issue: 10, 8427 - 8434, October 2024. 8 pages, 7 figures

Journal ref IEEE Robotics and Automation Letters Volume: 9, Issue: 10, 8427 - 8434, October 2024,

2107.04775 2021-09-22 cs.LG cs.AI cs.RO 60%

LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Sparse Reward Iterative Tasks

Albert Wilcox, Ashwin Balakrishna, Brijen Thananjeyan, Joseph E. Gonzalez, Ken Goldberg

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

Comments Conference on Robot Learning (CoRL) 2021. First two authors contributed equally

Journal ref Conference on Robot Learning (CoRL) 2021

1912.03509 2020-09-17 cs.RO cs.AI cs.LG 60%

Driving Style Encoder: Situational Reward Adaptation for General-Purpose Planning in Automated Driving

Sascha Rosbach, Vinit James, Simon Großjohann, Silviu Homoceanu, Xing Li, Stefan Roth

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

Comments To appear in Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Paris, France, June 2020 (Virtual Conference). Accepted version. Corrected figure font

Journal ref IEEE International Conference on Robotics and Automation (ICRA), Paris, France, 2020, pp. 6419-6425

1907.03423 2020-05-19 cs.LG cs.AI cs.RO 60%

On-Policy Robot Imitation Learning from a Converging Supervisor

Ashwin Balakrishna, Brijen Thananjeyan, Jonathan Lee, Felix Li, Arsh Zahed, Joseph E. Gonzalez, Ken Goldberg

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

Comments Conference on Robot Learning (CoRL) 2019 Oral. First two authors contributed equally

Journal ref 3rd Conference on Robot Learning (CoRL 2019)

1907.04799 2019-07-15 cs.RO cs.AI cs.LG 60%

RL-RRT: Kinodynamic Motion Planning via Learning Reachability Estimators from RL Policies

Hao-Tien Lewis Chiang, Jasmine Hsu, Marek Fiser, Lydia Tapia, Aleksandra Faust

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

Comments Accepted to Robotics and Automation Letters in June 2019

Journal ref Robotics and Automation Letters 2019

2608.18079 2026-08-20 cs.AI 新提交 57%

Position: Profiling Game Worlds by Transition Complexity

Position：通过转移复杂度分析游戏世界

Lele Cao

机构 * Microsoft Research（微软研究院）； DeepMind（深度思考（DeepMind））

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

AI总结该研究针对GWM与RL常被混淆的问题，提出转移复杂度剖面（TCP）指标，用于量化游戏环境的转移预测难度，呼吁其成为相关论文的标准基准元数据。

Comments Accepted by ICML 2026 Position Paper Track. https://icml.cc/virtual/2026/poster/67074

2608.17320 2026-08-19 cs.RO 新提交 57%

Robust Brachiation on a Life-Sized Dual-Arm Robot Using Waypoint-Guided Reinforcement Learning

使用路径点引导强化学习的真人大小双臂机器人的稳健摆臂运动

Ayumu Iwata, Kento Kawaharazuka, Keita Yoneda, Takahiro Hattori, Kei Okada

机构 * The University of Tokyo（东京大学）

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

AI总结本研究针对真人大小双臂机器人的稳健摆臂运动难题，提出路径点引导强化学习（WGRL）方法，结合路径点引导与任务成功、机械能奖励，经仿真与硬件实验验证，实现了含故障恢复的稳健摆臂，为机器人手臂运动设计提供指南。

Comments Accepted to 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

2507.15455 2026-08-19 math.NA cs.AI cs.NA math.AP 版本更新 57%

Solving nonconvex Hamilton--Jacobi--Isaacs equations with PINN-based policy iteration

用基于PINN的策略迭代求解非凸哈密顿-雅可比-艾萨克斯方程

Hee Jun Yang, Minjung Gim, Yeoneung Kim

机构 * National Institute for Mathematical Sciences（数学科学研究院）； Department of Applied Artificial Intelligence（应用人工智能系）

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

AI总结本文提出结合PINN与策略迭代的无网格框架，可求解高维非凸HJI方程，在两类数值实验中表现优于直接PINN求解器，具理论依据与应用潜力。

2608.16264 2026-08-18 cs.RO 新提交 57%

Cyclops: LiDAR as a Camera That Dreams in Color

Cyclops：以彩色进行“梦境”的相机式激光雷达

Wei Gao, Jian Shu, Mingle Zhao, Maani Ghaffari, David Kong, Chengzhong Xu, Hui Kong

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））； University of Michigan（密歇根大学）； University of Macau（澳门大学）

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

AI总结本文提出Cyclops框架，将稀疏NRS-LiDAR强度转为RGB视频，通过LBM等技术缓解帧间闪烁，合成RGB可使感知模型在多任务上优于LiDAR基线与传统相机。

1. 模仿学习与强化学习 4115 篇

An Incremental Inverse Reinforcement Learning Approach for Motion Planning with Separated Path and Velocity Preferences

Bayesian Disturbance Injection: Robust Imitation Learning of Flexible Policies

Adversarial Imitation Learning from Video using a State Observer

Learning to Rearrange with Physics-Inspired Risk Awareness

Hierarchical Reinforcement Learning under Mixed Observability

Reinforcement Learning with Videos: Combining Offline Observations with Interaction

Towards Hierarchical Task Decomposition using Deep Reinforcement Learning for Pick and Place Subtasks

DeepWalk: Omnidirectional Bipedal Gait by Deep Reinforcement Learning

Learning Variable Impedance Control via Inverse Reinforcement Learning for Force-Related Tasks

Hardware as Policy: Mechanical and Computational Co-Optimization using Deep Reinforcement Learning

"Good Robot!": Efficient Reinforcement Learning for Multi-Step Visual Tasks with Sim to Real Transfer

Visual Curiosity: Learning to Ask Questions to Learn Visual Recognition

Learning Neural Parsers with Deterministic Differentiable Imitation Learning

DART: Noise Injection for Robust Imitation Learning

CARLA: An Open Urban Driving Simulator

One-Shot Visual Imitation Learning via Meta-Learning

POMDP-lite for Robust Robot Planning under Uncertainty

SpatialThinker: Reinforcing Scene Graph-Grounded Spatial Reasoning via Dense Rewards

Deep Reinforcement Learning for Multi-Agent Coordination

Adaptive Torque Control of Exoskeletons under Spasticity Conditions via Reinforcement Learning

Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification Algorithms

Unsupervised Meta-Testing with Conditional Neural Processes for Hybrid Meta-Reinforcement Learning

LS3: Latent Space Safe Sets for Long-Horizon Visuomotor Control of Sparse Reward Iterative Tasks

Driving Style Encoder: Situational Reward Adaptation for General-Purpose Planning in Automated Driving

On-Policy Robot Imitation Learning from a Converging Supervisor

RL-RRT: Kinodynamic Motion Planning via Learning Reachability Estimators from RL Policies

Position: Profiling Game Worlds by Transition Complexity

Robust Brachiation on a Life-Sized Dual-Arm Robot Using Waypoint-Guided Reinforcement Learning

Solving nonconvex Hamilton--Jacobi--Isaacs equations with PINN-based policy iteration

Cyclops: LiDAR as a Camera That Dreams in Color