机器人 / 具身智能

Optimizing Deep Reinforcement Learning for Adaptive Robotic Arm Control

优化深度强化学习用于自适应机械臂控制

Jonaid Shianifar, Michael Schukat, Karl Mason

机构 * School of Computer Science, University of Galway（计算机科学学院，Galway大学） 纠错

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

AI总结 本文通过TPE优化SAC和PPO算法的超参数，显著提升了七自由度机械臂控制任务的算法性能和训练效率。

Journal ref PAAMS 2024, Communications in Computer and Information Science, vol 2149, PP 293-304 Springer, Cham (2025)

Mastering Contact-rich Tasks by Combining Soft and Rigid Robotics with Imitation Learning

Mariano Ramírez Montero, Ebrahim Shahabi, Giovanni Franzese, Jens Kober, Barbara Mazzolai, Cosimo Della Santina

机构 * Cognitive Robotics, Delft University of Technology（德鲁特理工大学认知机器人学） ； Bioinspired Soft Robotics Lab, Istituto Italiano di Tecnologia（意大利技术研究院仿生软机器人实验室） ； Technology Innovation Institute (TII)（技术创新研究所） ； Institute of Robotics and Mechatronics, German Aerospace Center (DLR)（德国航空航天中心机器人与机电研究所） 纠错

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

Comments Update with additional results and experiments

Multimodal Dreaming: A Global Workspace Approach to World Model-Based Reinforcement Learning

Léopold Maytié, Roland Bertin Johannet, Rufin VanRullen

机构 * Univ Toulouse, CNRS, CerCo, and ANITI, Artificial and Natural Intelligence Toulouse Institute（图卢兹大学、法国国家科学研究中心、CerCo以及ANITI人工智能与自然智能图卢兹研究所） 纠错

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

Comments Under review

Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement Learning

Yunpeng Jiang, Jianshu Hu, Paul Weng, Yutong Ban

机构 * Global College Shanghai Jiao Tong University（上海交通大学全球学院） ； Digital Innovation Research Center Duke Kunshan University（杜克大学昆山分校数字创新研究中心） 纠错

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

Comments Accepted in NeurIPS 2025

Reinforcement Learning with Lie Group Orientations for Robotics

Martin Schuck, Jan Brüdigam, Sandra Hirche, Angela Schoellig

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

Comments Submitted to ICRA 2025

Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models

Hao Wu, Yuan Gao, Xingjian Shi, Shuaipeng Li, Fan Xu, Fan Zhang, Zhihong Zhu, Weiyan Wang, Xiao Luo, Kun Wang, Xian Wu, Xiaomeng Huang

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

Medical Vision Language Models as Policies for Robotic Surgery

Akshay Muppidi, Martin Radfar

机构 * Department of Computer Science（计算机科学系） ； Stony Brook University（史泰尼斯布鲁克大学） 纠错

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

Comments IEEE CAI 2025

Journal ref 2025 IEEE Conference on Artificial Intelligence (CAI), Santa Clara, CA, USA, 2025, pp. 513,518

Safe Multi-Agent Navigation guided by Goal-Conditioned Safe Reinforcement Learning

Meng Feng, Viraj Parimi, Brian Williams

机构 * Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology（计算机科学与人工智能实验室，麻省理工学院） 纠错

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

Comments Due to the limitation "The abstract field cannot be longer than 1,920 characters", the abstract here is shorter than that in the PDF file

Jacobian Exploratory Dual-Phase Reinforcement Learning for Dynamic Endoluminal Navigation of Deformable Continuum Robots

Yu Tian, Chi Kit Ng, Hongliang Ren

机构 * The Department of Electronic Engineering, The Chinese University of Hong Kong（电子工程系，香港中文大学） 纠错

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

Improving Transformer World Models for Data-Efficient RL

Antoine Dedieu, Joseph Ortiz, Xinghua Lou, Carter Wendelken, Wolfgang Lehrach, J Swaroop Guntupalli, Miguel Lazaro-Gredilla, Kevin Patrick Murphy

机构 * Google DeepMind（谷歌DeepMind） 纠错

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

Comments ICML 2025

Continual Reinforcement Learning by Planning with Online World Models

Zichen Liu, Guoji Fu, Chao Du, Wee Sun Lee, Min Lin

机构 * Sea AI Lab（海智人工智能实验室） ； National University of Singapore（新加坡国立大学） 纠错

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

Comments ICML 2025 Spotlight

Continual Visual Reinforcement Learning with A Life-Long World Model

Minting Pan, Wendong Zhang, Geng Chen, Xiangming Zhu, Siyu Gao, Yunbo Wang, Xiaokang Yang

机构 * MoE Key Lab of Artificial Intelligence（人工智能MOE重点实验室） ； AI Institute（人工智能学院） ； Shanghai Jiao Tong University（上海交通大学） 纠错

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

Comments Accepted by ECML 2025

Reinforcement Learning with Physics-Informed Symbolic Program Priors for Zero-Shot Wireless Indoor Navigation

Tao Li, Haozhe Lei, Mingsheng Yin, Yaqi Hu

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

Comments Spotlight paper at Reinforcement Learning Conference 2025, Workshop on Inductive Biases in Reinforcement Learning

Robust Instant Policy: Leveraging Student's t-Regression Model for Robust In-context Imitation Learning of Robot Manipulation

Hanbit Oh, Andrea M. Salcedo-Vázquez, Ixchel G. Ramirez-Alpizar, Yukiyasu Domae

机构 * Industrial Cyber-Physical Systems Research Center at the National Institute of Advanced Industrial Science and Technology (AIST), Japan（日本国家先进工业科学技术研究院工业闭环系统研究中心） 纠错

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

Comments IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2025 accepted

Touch begins where vision ends: Generalizable policies for contact-rich manipulation

Zifan Zhao, Siddhant Haldar, Jinda Cui, Lerrel Pinto, Raunaq Bhirangi

机构 * New York University Shanghai（纽约大学上海分校） ； New York University（纽约大学） ； Honda Research（本田研究） 纠错

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

SGN-CIRL: Scene Graph-based Navigation with Curriculum, Imitation, and Reinforcement Learning

Nikita Oskolkov, Huzhenyu Zhang, Dmitry Makarov, Dmitry Yudin, Aleksandr Panov

机构 * Moscow Institute of Physics and Technology (MIPT)（莫斯科物理技术学院） ； Federal Research Center for Computer Science and Control of Russian Academy of Sciences（俄罗斯科学院计算机科学与控制联邦研究中心） ； Artificial Intelligence Research Institute (AIRI)（人工智能研究院） 纠错

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

Comments 7 pages, 11 figures

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks

Thomas Schmied, Thomas Adler, Vihang Patil, Maximilian Beck, Korbinian Pöppel, Johannes Brandstetter, Günter Klambauer, Razvan Pascanu, Sepp Hochreiter

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

CHEQ-ing the Box: Safe Variable Impedance Learning for Robotic Polishing

Emma Cramer, Lukas Jäschke, Sebastian Trimpe

机构 * Institute for Data Science in Mechanical Engineering（机械工程数据科学研究所） ； RWTH Aachen University（亚琛工业大学） 纠错

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

Novelty Detection in Reinforcement Learning with World Models

Geigh Zollicoffer, Kenneth Eaton, Jonathan Balloch, Julia Kim, Wei Zhou, Robert Wright, Mark O. Riedl

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

Comments ICML Spotlight 2025

Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation

Shuanghao Bai, Wanqi Zhou, Pengxiang Ding, Wei Zhao, Donglin Wang, Badong Chen

机构 * Shuanghao Bai（双浩白） ； Wanqi Zhou（王婉琪） ； Pengxiang Ding（丁鹏祥） ； Wei Zhao（赵伟） ； Donglin Wang（王东林） ； Badong Chen（陈Badong） 纠错

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

Comments Accepted by ICML 2025

ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics

Letian Chen, Nina Moorman, Matthew Gombolay

机构 * School of Interactive Computing, Georgia Institute of Technology, Atlanta, United States（交互计算学院，佐治亚理工学院，美国亚特兰大） ； Department of XXX, University of YYY, Location, Country（XXX系，YYY大学，Location Country） ； School of ZZZ, Institute of WWW, Location, Country（ZZZ学院，WWW研究所，Location Country） 纠错

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

Comments ICML 2025

Automated Hybrid Reward Scheduling via Large Language Models for Robotic Skill Learning

Changxin Huang, Junyang Liang, Yanbin Chang, Jingzhao Xu, Jianqiang Li

机构 * National Engineering Laboratory for Big Data System Computing Technology（大数据系统计算技术国家工程实验室） 纠错

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

Neural Motion Simulator: Pushing the Limit of World Models in Reinforcement Learning

Chenjie Hao, Weyl Lu, Yifan Xu, Yubei Chen

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

Comments 8 pages (main), 2-page appendix, 8 figures, accepted by CVPR 2025

Deep RL-based Autonomous Navigation of Micro Aerial Vehicles (MAVs) in a complex GPS-denied Indoor Environment

Amit Kumar Singh, Prasanth Kumar Duba, P. Rajalakshmi

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

Value Iteration for Learning Concurrently Executable Robotic Control Tasks

Sheikh A. Tahmid, Gennaro Notomista

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

Comments To be published in AAMAS 2025 conference: https://aamas2025.org/

Reinforcement Learning for Safe Autonomous Two Device Navigation of Cerebral Vessels in Mechanical Thrombectomy

Harry Robertshaw, Benjamin Jackson, Jiaheng Wang, Hadi Sadati, Lennart Karstensen, Alejandro Granados, Thomas C Booth

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

Journal ref Int J CARS (2025)

Bresa: Bio-inspired Reflexive Safe Reinforcement Learning for Contact-Rich Robotic Tasks

Heng Zhang, Gokhan Solak, Arash Ajoudani

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

Comments submitted to IEEE RA-L

DITTO: Offline Imitation Learning with World Models

Branton DeMoss, Paul Duckworth, Jakob Foerster, Nick Hawes, Ingmar Posner

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

Robotic Paper Wrapping by Learning Force Control

Hiroki Hanai, Takuya Kiyokawa, Weiwei Wan, Kensuke Harada

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

Safe Continual Domain Adaptation after Sim2Real Transfer of Reinforcement Learning Policies in Robotics

Josip Josifovski, Shangding Gu, Mohammadhossein Malmir, Haoliang Huang, Sayantan Auddy, Nicolás Navarro-Guerrero, Costas Spanos, Alois Knoll

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

Comments 8 pages, 5 figures, under review