机器人 / 具身智能 - arXivDaily 专题

2510.18485 2025-10-22 cs.LG 57%

Learning to Navigate Under Imperfect Perception: Conformalised Segmentation for Safe Reinforcement Learning

Daniel Bethell, Simos Gerasimou, Radu Calinescu, Calum Imrie

机构 * University of York（约克大学）

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

2510.17086 2025-10-21 cs.RO 57%

Learning to Design Soft Hands using Reward Models

Xueqian Bai, Nicklas Hansen, Adabhav Singh, Michael T. Tolley, Yan Duan, Pieter Abbeel, Xiaolong Wang, Sha Yi

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

2510.15388 2025-10-20 cs.LG 57%

Iterative Refinement of Flow Policies in Probability Space for Online Reinforcement Learning

Mingyang Sun, Pengxiang Ding, Weinan Zhang, Donglin Wang

机构 * Shanghai Innovation Institute（上海创新研究院）； Shanghai Jiao Tong University（上海交通大学）

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

2510.04168 2025-10-20 cs.RO cs.SY eess.SY 57%

Learning to Capture Rocks using an Excavator: A Reinforcement Learning Approach with Guiding Reward Formulation

Amirmasoud Molaei, Mohammad Heravi, Reza Ghabcheloo

机构 * Faculty of Engineering and Natural Sciences, Tampere University（工程与自然科学学院，塔尔皮亚大学）

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

2510.14946 2025-10-17 eess.IV cs.RO 57%

EdgeNavMamba: Mamba Optimized Object Detection for Energy Efficient Edge Devices

Romina Aalishah, Mozhgan Navardi, Tinoosh Mohsenin

机构 * Department of Electrical and Computer Engineering（电气与计算机工程系）； Johns Hopkins University（约翰霍普金斯大学）

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

Comments The 11th IEEE International Conference on Edge Computing and Scalable Cloud (IEEE EdgeCom 2025)

2510.14783 2025-10-17 cs.RO 57%

SkyDreamer: Interpretable End-to-End Vision-Based Drone Racing with Model-Based Reinforcement Learning

Aderik Verraest, Stavrow Bahnam, Robin Ferede, Guido de Croon, Christophe De Wagter

机构 * Faculty of Aerospace Engineering, Delft University of Technology（航空航天工程学院，代尔夫特理工大学）

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

2510.14467 2025-10-17 cs.RO 57%

Restoring Noisy Demonstration for Imitation Learning With Diffusion Models

Shang-Fu Chen, Co Yong, Shao-Hua Sun

机构 * Graduate Institute of Communication Engineering, National Taiwan University（国立台湾大学通信工程研究所）； Data Science Degree Program, National Taiwan University and Academia Sinica（国立台湾大学数据科学学士学位计划）； Department of Electrical Engineering, National Taiwan University（国立台湾大学电子工程系）

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

Comments Published in IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

Journal ref IEEE Transactions on Neural Networks and Learning Systems (TNNLS), pp. 1-13, Sept. 2025

2510.13826 2025-10-17 q-bio.NC cs.AI 57%

Towards Neurocognitive-Inspired Intelligence: From AI's Structural Mimicry to Human-Like Functional Cognition

Noorbakhsh Amiri Golilarz, Hassan S. Al Khatib, Shahram Rahimi

机构 * Department of Computer Science, The University of Alabama（计算机科学系，阿拉巴马大学）

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

2510.13809 2025-10-16 cs.CV 57%

PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning

Sihui Ji, Xi Chen, Xin Tao, Pengfei Wan, Hengshuang Zhao

机构 * The University of Hong Kong（香港大学）； Kling Team, Kuaishou Technology（快手科技 Kling 团队）

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

Comments Project Page: https://sihuiji.github.io/PhysMaster-Page/

2510.10975 2025-10-15 cs.RO 57%

RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Model

Mingtong Dai, Lingbo Liu, Yongjie Bai, Yang Liu, Zhouxia Wang, Rui SU, Chunjie Chen, Liang Lin, Xinyu Wu

机构 * Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究所）； Peng Cheng Laboratory（鹏城实验室）； School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）； College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）； Shanghai AI Laboratory（上海人工智能实验室）； University of Chinese Academy of Sciences（中国科学院大学）； X-Era AI Lab（X-Era人工智能实验室）

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

2510.11307 2025-10-14 cs.CL cs.AI 57%

FOSSIL: Harnessing Feedback on Suboptimal Samples for Data-Efficient Generalisation with Imitation Learning for Embodied Vision-and-Language Tasks

Sabrina McCallum, Amit Parekh, Alessandro Suglia

机构 * University of Edinburgh（爱丁堡大学）； Heriot-Watt University（赫瑞思-瓦特大学）

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

Comments EMNLP 2025 Findings

2510.10960 2025-10-14 cs.RO 57%

Game-Theoretic Risk-Shaped Reinforcement Learning for Safe Autonomous Driving

Dong Hu, Fenqing Hu, Lidong Yang, Chao Huang

机构 * Department of Industrial and Systems Engineering, the Hong Kong Polytechnic University（工业与系统工程系，香港理工大学）

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

2510.08787 2025-10-13 cs.RO 57%

Geometry-aware Policy Imitation

Yiming Li, Nael Darwiche, Amirreza Razmjoo, Sichao Liu, Yilun Du, Auke Ijspeert, Sylvain Calinon

机构 * Idiap Research Institute（Idiap研究机构）； EPFL（瑞士联邦理工学院）； Harvard University（哈佛大学）

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

Comments 21 pages, 13 figures. In submission

2509.06782 2025-10-10 cs.LG 57%

Physics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning

Vittorio Giammarino, Ruiqi Ni, Ahmed H. Qureshi

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

2510.04076 2025-10-07 cs.RO cs.SY eess.SY 57%

From Shadow to Light: Toward Safe and Efficient Policy Learning Across MPC, DeePC, RL, and LLM Agents

Amin Vahidi-Moghaddam, Sayed Pedram Haeri Boroujeni, Iman Jebellat, Ehsan Jebellat, Niloufar Mehrabi, Zhaojian Li

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

2505.19281 2025-10-07 cs.LG 57%

A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning

Yuzheng Hu, Fan Wu, Haotian Ye, David Forsyth, James Zou, Nan Jiang, Jiaqi W. Ma, Han Zhao

机构 * UIUC Urbana（伊利诺伊大学 Urbana分校）； Stanford University（斯坦福大学）

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

Comments Accepted at NeurIPS 2025 as an oral

2510.01843 2025-10-03 cs.RO 57%

Like Playing a Video Game: Spatial-Temporal Optimization of Foot Trajectories for Controlled Football Kicking in Bipedal Robots

Wanyue Li, Ji Ma, Minghao Lu, Peng Lu

机构 * Adaptive Robotic Controls Lab (ArcLab), Department of Mechanical Engineering, The University of Hong Kong（适应性机器人控制实验室（ArcLab）、机械工程系、香港大学）

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

Comments 8 pages, 8 figures, conference paper

2510.01083 2025-10-02 cs.LG 57%

Multi-Actor Multi-Critic Deep Deterministic Reinforcement Learning with a Novel Q-Ensemble Method

Andy Wu, Chun-Cheng Lin, Rung-Tzuo Liaw, Yuehua Huang, Chihjung Kuo, Chia Tong Weng

机构 * csie.fju.edu.tw（逢甲大学计算机科学系）

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

2509.26137 2025-10-01 cs.LG 57%

Accelerating Transformers in Online RL

Daniil Zelezetsky, Alexey K. Kovalev, Aleksandr I. Panov

机构 * Cognitive AI Lab（认知人工智能实验室）

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

2509.26082 2025-10-01 cs.RO 57%

Evolutionary Continuous Adaptive RL-Powered Co-Design for Humanoid Chin-Up Performance

Tianyi Jin, Melya Boukheddimi, Rohit Kumar, Gabriele Fadini, Frank Kirchner

机构 * Robotics Innovation Center, DFKI GmbH（DFKI机器人创新中心）； Computational Robotics Lab, ETH Zurich（苏黎世联邦理工学院计算机器人实验室）； AG Robotik University of Bremen（不莱梅大学机器人技术研究所）； RWTH Aachen University（亚琛工业大学）

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

2505.09308 2025-10-01 cs.LG 57%

Neural Multivariate Regression: Qualitative Insights from the Unconstrained Feature Model

George Andriopoulos, Soyuj Jung Basnet, Juan Guevara, Li Guo, Keith Ross

机构 * New York University Abu Dhabi（纽约大学阿布扎克分校）； New York University Shanghai（纽约大学上海分校）； New York University（纽约大学）； MBZUAI（马斯喀特人工智能研究所）

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

Comments 35 pages, 10 figures

2509.19752 2025-09-30 cs.RO 57%

Beyond Human Demonstrations: Diffusion-Based Reinforcement Learning to Generate Data for VLA Training

Rushuai Yang, Hangxing Wei, Ran Zhang, Zhiyuan Feng, Xiaoyu Chen, Tong Li, Chuheng Zhang, Li Zhao, Jiang Bian, Xiu Su, Yi Chen

机构 * Hong Kong University of Science and Technology（香港科技大学）； Microsoft Research Asia（微软亚洲研究院）； Wuhan University（武汉大学）； University of Chinese Academy of Sciences（中国科学院大学）； Tsinghua University（清华大学）； Big Data Institute, Central South University（中南大学大数据研究院）

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

2509.23220 2025-09-30 cs.RO 57%

GLUE: Global-Local Unified Encoding for Imitation Learning via Key-Patch Tracking

Ye Chen, Zichen Zhou, Jianyu Dou, Te Cui, Yi Yang, Yufeng Yue

机构 * Beijing Institute of Technology（北京理工大学）

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

Comments 8 pages, 5 figures

2509.23219 2025-09-30 cs.LG 57%

WirelessMathLM: Teaching Mathematical Reasoning for LLMs in Wireless Communications with Reinforcement Learning

Xin Li, Mengbing Liu, Yiyang Zhu, Wenhe Zhang, Li Wei, Jiancheng An, Chau Yuen

机构 * Nanyang Technological University（南洋理工大学）

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

Comments Project Homepage: https://lixin.ai/WirelessMathLM

2509.16757 2025-09-30 cs.RO 57%

HDMI: Learning Interactive Humanoid Whole-Body Control from Human Videos

Haoyang Weng, Yitang Li, Nikhil Sobanbabu, Zihan Wang, Zhengyi Luo, Tairan He, Deva Ramanan, Guanya Shi

机构 * Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）

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

Comments website: hdmi-humanoid.github.io

2509.20541 2025-09-26 cs.RO 57%

Selective Progress-Aware Querying for Human-in-the-Loop Reinforcement Learning

Anujith Muraleedharan, Anamika J H

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

Comments Preprint. 8 pages, 3 figures, 1 table, 1 algorithm. CoRL 2025 style (preprint). Code/data to be released

2503.07848 2025-09-26 cs.AI 57%

Safe Explicable Policy Search

Akkamahadevi Hanni, Jonathan Montaño, Yu Zhang

机构 * School of Computing and Augmented Intelligence, Arizona State University（计算与增强智能学院，亚利桑那州立大学）； School of Mathematical and Statistical Sciences, Arizona State University（数学与统计科学学院，亚利桑那州立大学）

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

2509.14453 2025-09-22 cs.RO cs.MA cs.SY eess.SY 57%

Online Learning of Deceptive Policies under Intermittent Observation

Gokul Puthumanaillam, Ram Padmanabhan, Jose Fuentes, Nicole Cruz, Paulo Padrao, Ruben Hernandez, Hao Jiang, William Schafer, Leonardo Bobadilla, Melkior Ornik

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）； Providence College（普罗维登斯学院）； Florida International University（佛罗里达国际大学）

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

2508.03693 2025-09-22 cs.LG 57%

PAC Apprenticeship Learning with Bayesian Active Inverse Reinforcement Learning

Ondrej Bajgar, Dewi S. W. Gould, Jonathon Liu, Alessandro Abate, Konstantinos Gatsis, Michael A. Osborne

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

Comments Presented at RLC 2025; published in RLJ 2025

Journal ref Reinforcement Learning Journal 2025

2509.13200 2025-09-22 cs.RO 57%

StageACT: Stage-Conditioned Imitation for Robust Humanoid Door Opening

Moonyoung Lee, Dong Ki Kim, Jai Krishna Bandi, Max Smith, Aileen Liao, Ali-akbar Agha-mohammadi, Shayegan Omidshafiei

机构 * Carnegie Mellon University（卡内基梅隆大学）； University of Pennsylvania（宾夕法尼亚大学）

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

Comments 7 pages

1. 模仿学习与强化学习 4134 篇

Learning to Navigate Under Imperfect Perception: Conformalised Segmentation for Safe Reinforcement Learning

Learning to Design Soft Hands using Reward Models

Iterative Refinement of Flow Policies in Probability Space for Online Reinforcement Learning

Learning to Capture Rocks using an Excavator: A Reinforcement Learning Approach with Guiding Reward Formulation

EdgeNavMamba: Mamba Optimized Object Detection for Energy Efficient Edge Devices

SkyDreamer: Interpretable End-to-End Vision-Based Drone Racing with Model-Based Reinforcement Learning

Restoring Noisy Demonstration for Imitation Learning With Diffusion Models

Towards Neurocognitive-Inspired Intelligence: From AI's Structural Mimicry to Human-Like Functional Cognition

PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning

RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Model

FOSSIL: Harnessing Feedback on Suboptimal Samples for Data-Efficient Generalisation with Imitation Learning for Embodied Vision-and-Language Tasks

Game-Theoretic Risk-Shaped Reinforcement Learning for Safe Autonomous Driving

Geometry-aware Policy Imitation

Physics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning

From Shadow to Light: Toward Safe and Efficient Policy Learning Across MPC, DeePC, RL, and LLM Agents

A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning

Like Playing a Video Game: Spatial-Temporal Optimization of Foot Trajectories for Controlled Football Kicking in Bipedal Robots

Multi-Actor Multi-Critic Deep Deterministic Reinforcement Learning with a Novel Q-Ensemble Method

Accelerating Transformers in Online RL

Evolutionary Continuous Adaptive RL-Powered Co-Design for Humanoid Chin-Up Performance

Neural Multivariate Regression: Qualitative Insights from the Unconstrained Feature Model

Beyond Human Demonstrations: Diffusion-Based Reinforcement Learning to Generate Data for VLA Training

GLUE: Global-Local Unified Encoding for Imitation Learning via Key-Patch Tracking

WirelessMathLM: Teaching Mathematical Reasoning for LLMs in Wireless Communications with Reinforcement Learning

HDMI: Learning Interactive Humanoid Whole-Body Control from Human Videos

Selective Progress-Aware Querying for Human-in-the-Loop Reinforcement Learning

Safe Explicable Policy Search

Online Learning of Deceptive Policies under Intermittent Observation

PAC Apprenticeship Learning with Bayesian Active Inverse Reinforcement Learning

StageACT: Stage-Conditioned Imitation for Robust Humanoid Door Opening