arXivDaily arXiv每日学术速递 周一至周五更新

视觉与机器人

机器人 / 具身智能

机器人、具身智能、机器人学习、操作、导航和具身世界模型。

共收录 4103 信号源:cs.RO, cs.AI, cs.CV, cs.LG

1. 模仿学习与强化学习 4103 篇

2502.20168 2025-02-28 cs.RO cs.AI cs.LG cs.NE stat.ML 87%

Accelerating Model-Based Reinforcement Learning with State-Space World Models

Maria Krinner, Elie Aljalbout, Angel Romero, Davide Scaramuzza

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.11484 2024-12-17 cs.AI cs.CV cs.RO 87%

Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents

Wonje Choi, Woo Kyung Kim, SeungHyun Kim, Honguk Woo

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

Comments Accepted at NeurIPS 2023

详情

展开后加载摘要…

URL PDF HTML 收藏
2310.02635 2024-10-14 cs.RO cs.AI cs.LG 87%

Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own

Weirui Ye, Yunsheng Zhang, Haoyang Weng, Xianfan Gu, Shengjie Wang, Tong Zhang, Mengchen Wang, Pieter Abbeel, Yang Gao

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

Comments CoRL 2024 (Oral)

详情

展开后加载摘要…

URL PDF HTML 收藏
2311.02379 2023-11-07 cs.RO cs.AI cs.LG 87%

Accelerating Reinforcement Learning of Robotic Manipulations via Feedback from Large Language Models

Kun Chu, Xufeng Zhao, Cornelius Weber, Mengdi Li, Stefan Wermter

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

Comments CoRL 2023 Workshop (oral)

详情

展开后加载摘要…

URL PDF HTML 收藏
2309.13041 2023-09-25 cs.RO cs.CV cs.LG 87%

Robotic Offline RL from Internet Videos via Value-Function Pre-Training

Chethan Bhateja, Derek Guo, Dibya Ghosh, Anikait Singh, Manan Tomar, Quan Vuong, Yevgen Chebotar, Sergey Levine, Aviral Kumar

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

Comments First three authors contributed equally

详情

展开后加载摘要…

URL PDF HTML 收藏
2112.01163 2021-12-03 cs.LG cs.AI cs.RO 87%

Robust Robotic Control from Pixels using Contrastive Recurrent State-Space Models

Nitish Srivastava, Walter Talbott, Martin Bertran Lopez, Shuangfei Zhai, Josh Susskind

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

Comments NeurIPS Deep Reinforcement Learning Workshop 2021. Code can be found at https://github.com/apple/ml-core

详情

展开后加载摘要…

URL PDF HTML 收藏
2004.10190 2020-08-03 cs.LG cs.CV cs.RO stat.ML 87%

Never Stop Learning: The Effectiveness of Fine-Tuning in Robotic Reinforcement Learning

Ryan Julian, Benjamin Swanson, Gaurav S. Sukhatme, Sergey Levine, Chelsea Finn, Karol Hausman

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

Comments 8.5 pages, 9 figures. See video overview and experiments at https://youtu.be/pPDVewcSpdc and project website at https://ryanjulian.me/continual-fine-tuning

详情

展开后加载摘要…

URL PDF HTML 收藏
2007.13715 2020-07-28 cs.RO cs.CV cs.LG 87%

Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation

Kenzo Lobos-Tsunekawa, Tatsuya Harada

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

Comments Accepted to IROS'2020

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.02228 2026-01-06 cs.LG cs.AI 87%

Coupled Distributional Random Expert Distillation for World Model Online Imitation Learning

世界模型在线模仿学习中的耦合分布随机专家蒸馏

Shangzhe Li, Zhiao Huang, Hao Su

机构 * UNC Chapel Hill(北卡罗来纳大学教堂山分校) Hillbot(Hillbot公司) University of California, San Diego(加州大学圣地亚哥分校)

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

AI总结 本研究提出一种基于随机网络蒸馏的耦合分布随机专家蒸馏方法,用于提升世界模型在线模仿学习的稳定性与性能。

Comments NeurIPS 2025 Workshop of Embodied World Models; Code Available at: https://github.com/TobyLeelsz/CDRED-WM

详情

展开后加载摘要…

URL PDF HTML 收藏
2107.09822 2023-04-05 cs.RO cs.AI cs.SY eess.SY 87%

Bayesian Controller Fusion: Leveraging Control Priors in Deep Reinforcement Learning for Robotics

Krishan Rana, Vibhavari Dasagi, Jesse Haviland, Ben Talbot, Michael Milford, Niko Sünderhauf

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

Comments The International Journal of Robotics Research (IJRR), 2023. Project page: https://krishanrana.github.io/bcf

详情

展开后加载摘要…

URL PDF HTML 收藏
2202.02005 2022-02-07 cs.RO cs.LG 87%

BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning

Eric Jang, Alex Irpan, Mohi Khansari, Daniel Kappler, Frederik Ebert, Corey Lynch, Sergey Levine, Chelsea Finn

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

Comments CoRL 2021, 23 pages

Journal ref Conference on Robot Learning (pp. 991-1002). 2022 Jan 11

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.22907 2026-06-23 cs.RO cs.CV 新提交 86%

Improving Robotic Imitation Learning via Trajectory Standardization

通过轨迹标准化改进机器人模仿学习

Licheng Yang, Lingfeng Qian, Fei Zheng, Yonghao He, Wei Sui, Shuangshuang Li, Hu Su

机构 * State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所多模态人工智能系统国家重点实验室) D-Robotics

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

AI总结 针对人类演示轨迹中的噪声和速度不均匀问题,提出信息标准化轨迹重采样(ISR)方法,通过信息流形上的测地等距参数化去除冗余,在三个真实操作任务中成功率提升约25%。

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.19544 2026-06-16 cs.LG cs.RO 版本更新 86%

Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data

通过非策划数据引导世界模型的高效强化学习

Yi Zhao, Aidan Scannell, Wenshuai Zhao, Yuxin Hou, Tianyu Cui, Le Chen, Dieter Büchler, Arno Solin, Juho Kannala, Joni Pajarinen

机构 * Aalto University(阿alto大学) University of Edinburgh(爱丁堡大学) ELLIS Institute Finland(芬兰ELLIS研究所) Deep Render Imperial College London(伦敦帝国理工学院) Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所) CIFAR AI Chair(CIFAR人工智能主席) University of Alberta(阿尔伯塔大学) Alberta Machine Intelligence Institute (Amii)(阿尔伯塔机器智能研究所(Amii)) University of Oulu(奥卢大学)

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

AI总结 提出利用无奖励、混合质量、多本体的非策划离线数据,通过经验回放和执行引导技术解决分布偏移问题,显著提升在线强化学习的样本效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.21758 2026-03-17 cs.RO cs.LG 86%

Taxonomy and Trends in Reinforcement Learning for Robotics and Control Systems: A Structured Review

强化学习在机器人与控制系统中的分类与趋势:一种结构化综述

Kumater Ter, Abolanle Adetifa, Daniel Udekwe

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

AI总结 本文综述了强化学习原理、深度强化学习算法及其在机器人和控制系统中的应用,探讨了核心算法策略及现代DRL技术,旨在连接理论进展与实际应用。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.11110 2026-03-13 cs.RO cs.AI 86%

ResWM: Residual-Action World Model for Visual RL

ResWM:基于视觉强化学习的残差动作世界模型

Jseen Zhang, Gabriel Adineera, Jinzhou Tan, Jinoh Kim

机构 * University of California, San Diego(加州大学圣地亚哥分校) Texas A&M University-Commerce(德克萨斯A&M大学-科摩斯)

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

AI总结 ResWM通过将控制变量从绝对动作转换为残差动作,提升了视觉强化学习中世界模型的预测能力和稳定性,实现了更高效的样本利用和更平滑的控制策略。

Comments Submit KDD2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.11978 2026-03-10 cs.RO cs.AI 86%

Accelerating Robotic Reinforcement Learning with Agent Guidance

通过代理引导加速机器人强化学习

Haojun Chen, Zili Zou, Chengdong Ma, Yaoxiang Pu, Haotong Zhang, Yuanpei Chen, Yaodong Yang

机构 * Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院) PKU-PsiBot Joint Lab(北京大学- PsiBot 联合实验室)

专题命中 模仿学习与强化学习 :robotic(title);robot learning(abstract);manipulation(abstract);world model(abstract)

AI总结 AGPS通过多模态代理替代人类监督,提升机器人强化学习的样本效率和可扩展性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.02454 2026-02-03 cs.RO cs.AI 86%

World-Gymnast: Training Robots with Reinforcement Learning in a World Model

World-Gymnast: 在世界模型中用强化学习训练机器人

Ansh Kumar Sharma, Yixiang Sun, Ninghao Lu, Yunzhe Zhang, Jiarao Liu, Sherry Yang

机构 * New York University(纽约大学) University of California, Berkeley(加州大学伯克利分校)

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

AI总结 World-Gymnast通过在世界模型中进行强化学习微调,有效提升真实机器人性能,比监督学习和软件模拟更具优势。

Comments https://world-gymnast.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.17135 2026-01-27 cs.LG cs.RO 86%

ConceptACT: Episode-Level Concepts for Sample-Efficient Robotic Imitation Learning

ConceptACT: 用于样本高效机器人模仿学习的事件级概念

Jakob Karalus, Friedhelm Schwenker

机构 * Institute of Artificial Intelligence, Ulm University(人工智能研究所,乌尔姆大学) Institute of Neuroinformatics, Ulm University(神经信息研究所,乌尔姆大学)

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

AI总结 ConceptACT通过整合事件级语义概念提升机器人模仿学习的样本效率,采用改进的Transformer架构实现概念感知的交叉注意力,实验表明其在收敛速度和样本效率上优于标准ACT。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.12428 2026-01-21 cs.RO cs.CV 86%

ReWorld: Multi-Dimensional Reward Modeling for Embodied World Models

ReWorld:面向具身世界模型的多维奖励建模

Baorui Peng, Wenyao Zhang, Liang Xu, Zekun Qi, Jiazhao Zhang, Hongsi Liu, Wenjun Zeng, Xin Jin

机构 * Eastern Institute of Technology(东部技术研究所) Georgia Institute of Technology(佐治亚理工学院) Shanghai Jiao Tong University(上海交通大学) Tsinghua University(清华大学) University of Science and Technology of China(中国科学技术大学) Peking University(北京大学)

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

AI总结 ReWorld通过多维奖励建模提升具身世界模型的物理真实性和任务完成能力

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.15327 2025-12-01 cs.RO cs.LG 86%

Advancing Embodied Intelligence in Robotic-Assisted Endovascular Procedures: A Systematic Review of AI Solutions

推进机器人辅助血管内手术中的具身智能:人工智能解决方案的系统综述

Tianliang Yao, Bo Lu, Markus Kowarschik, Yixuan Yuan, Hubin Zhao, Sebastien Ourselin, Kaspar Althoefer, Junbo Ge, Peng Qi

机构 * Department of Control Science and Engineering, College of Electronics and Information Engineering, and Shanghai Institute of Intelligent Science and Technology, Tongji University(控制科学与工程系,电子信息工程学院,上海智能科学技术研究院,同济大学) Department of Electronic Engineering, Faculty of Engineering, The Chinese University of Hong Kong(电子工程系,工程学院,香港中文大学) Robotics and Microsystems Center, School of Mechanical and Electrical Engineering, Soochow University(机器人与微系统中心,机械与电气工程学院,苏州大学) Siemens Healthineers Advanced Therapies (AT), Forchheim, Bavaria(西门子医疗先进治疗(AT), Forchheim, 巴伐利亚) HUB of Intelligent Neuro-Engineering (HUBIN), CREATe, Division of Surgery & Interventional Science, University College London(智能神经工程中心(HUBIN),CREATE,外科与介入科学系,伦敦大学学院) School of Biomedical Engineering & Imaging Sciences, King’s College London(生物医学工程与成像科学学院,伦敦国王学院)

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

AI总结 本文系统综述了人工智能在机器人辅助血管内手术中具身智能的应用,探讨了其挑战与未来发展方向。

Comments 20 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.09515 2025-11-13 cs.RO cs.AI 86%

WMPO: World Model-based Policy Optimization for Vision-Language-Action Models

Fangqi Zhu, Zhengyang Yan, Zicong Hong, Quanxin Shou, Xiao Ma, Song Guo

机构 * Hong Kong University of Science and Technology(香港科学与技术大学) ByteDance Seed(字节跳动种子)

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

Comments project website: https://wm-po.github.io

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.19555 2025-07-29 cs.RO cs.AI 86%

Extending Group Relative Policy Optimization to Continuous Control: A Theoretical Framework for Robotic Reinforcement Learning

Rajat Khanda, Mohammad Baqar, Sambuddha Chakrabarti, Satyasaran Changdar

机构 * University of Houston(德克萨斯大学) Cisco Systems(思科系统) Princeton University(普林斯顿大学) University of Copenhagen(哥本哈根大学)

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

Comments 13 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.13498 2025-06-17 cs.RO cs.HC cs.LG cs.SY eess.SY 86%

A Survey on Imitation Learning for Contact-Rich Tasks in Robotics

Toshiaki Tsuji, Yasuhiro Kato, Gokhan Solak, Heng Zhang, Tadej Petrič, Francesco Nori, Arash Ajoudani

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

Comments 47pages, 1 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.01867 2024-04-03 cs.RO cs.LG 86%

Active Exploration in Bayesian Model-based Reinforcement Learning for Robot Manipulation

Carlos Plou, Ana C. Murillo, Ruben Martinez-Cantin

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2307.15944 2023-08-01 cs.RO cs.LG 86%

PIMbot: Policy and Incentive Manipulation for Multi-Robot Reinforcement Learning in Social Dilemmas

Shahab Nikkhoo, Zexin Li, Aritra Samanta, Yufei Li, Cong Liu

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

Comments Accepted at IROS2023

详情

展开后加载摘要…

URL PDF HTML 收藏
2110.08003 2021-11-19 cs.RO cs.AI 86%

A Broad-persistent Advising Approach for Deep Interactive Reinforcement Learning in Robotic Environments

Hung Son Nguyen, Francisco Cruz, Richard Dazeley

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

Comments 10 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2101.04178 2021-04-20 cs.RO cs.LG 86%

Action Priors for Large Action Spaces in Robotics

Ondrej Biza, Dian Wang, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong

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

Comments 13 pages, 9 figures

Journal ref Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS '21). 2021. 205 - 213

详情

展开后加载摘要…

URL PDF HTML 收藏
2004.12570 2020-04-28 cs.LG cs.RO stat.ML 86%

The Ingredients of Real-World Robotic Reinforcement Learning

Henry Zhu, Justin Yu, Abhishek Gupta, Dhruv Shah, Kristian Hartikainen, Avi Singh, Vikash Kumar, Sergey Levine

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

Comments First three authors contributed equally. Accepted as a spotlight presentation at ICLR 2020

详情

展开后加载摘要…

URL PDF HTML 收藏
1703.07261 2017-07-25 cs.RO cs.LG 86%

Black-Box Data-efficient Policy Search for Robotics

Konstantinos Chatzilygeroudis, Roberto Rama, Rituraj Kaushik, Dorian Goepp, Vassilis Vassiliades, Jean-Baptiste Mouret

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

Comments Accepted at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2017; Code at http://github.com/resibots/blackdrops; Video at http://youtu.be/kTEyYiIFGPM

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.07380 2025-09-03 cs.RO 86%

Wheeled Lab: Modern Sim2Real for Low-cost, Open-source Wheeled Robotics

Tyler Han, Preet Shah, Sidharth Rajagopal, Yanda Bao, Sanghun Jung, Sidharth Talia, Gabriel Guo, Bryan Xu, Bhaumik Mehta, Emma Romig, Rosario Scalise, Byron Boots

机构 * University of Washington(华盛顿大学)

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

Comments To appear at Conference on Robot Learning, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏