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 4106 信号源:cs.RO, cs.AI, cs.CV, cs.LG

1. 模仿学习与强化学习 4106 篇

2010.14838 2020-11-30 cs.RO 79%

Dynamically Feasible Deep Reinforcement Learning Policy for Robot Navigation in Dense Mobile Crowds

Utsav Patel, Nithish Kumar, Adarsh Jagan Sathyamoorthy, Dinesh Manocha

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

Comments 9 pages, 13 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2008.02116 2020-08-06 cs.RO cs.NE 79%

Quality and Diversity in Evolutionary Modular Robotics

Jørgen Nordmoen, Frank Veenstra, Kai Olav Ellefsen, Kyrre Glette

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2007.10835 2020-07-22 cs.CV 79%

Soft Expert Reward Learning for Vision-and-Language Navigation

Hu Wang, Qi Wu, Chunhua Shen

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2007.09300 2020-07-21 cs.AI 79%

An Open-World Simulated Environment for Developmental Robotics

SM Mazharul Islam, Md Ashaduzzaman Rubel Mondol, Aishwarya Pothula, Deokgun Park

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

Comments Presented at Workshop on Learning in Artificial Open Worlds held with ICML 2020

详情

展开后加载摘要…

URL PDF HTML 收藏
2003.02740 2020-03-06 cs.LG stat.ML 79%

Balance Between Efficient and Effective Learning: Dense2Sparse Reward Shaping for Robot Manipulation with Environment Uncertainty

Yongle Luo, Kun Dong, Lili Zhao, Zhiyong Sun, Chao Zhou, Bo Song

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2001.03877 2020-01-14 cs.LG stat.ML 79%

Deep Reinforcement Learning for Complex Manipulation Tasks with Sparse Feedback

Binyamin Manela

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

Comments A thesis submitted in fulfillment of the requirements for the degree of Master of Science in the department of Industrial Engineering and Management at Ben-Gurion University of the Negev

详情

展开后加载摘要…

URL PDF HTML 收藏
1907.00388 2019-07-11 cs.RO cs.SY eess.SY 79%

Reinforcement Learning for Robotic Time-optimal Path Tracking Using Prior Knowledge

Jiadong Xiao, Lin Li, Yanbiao Zou, Tie Zhang

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

Comments 27 pages, 14 figures, 4 Tables

详情

展开后加载摘要…

URL PDF HTML 收藏
1902.05183 2019-02-15 cs.RO 79%

Manipulating Soft Tissues by Deep Reinforcement Learning for Autonomous Robotic Surgery

Ngoc Duy Nguyen, Thanh Nguyen, Saeid Nahavandi, Asim Bhatti, Glenn Guest

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

详情

展开后加载摘要…

URL PDF HTML 收藏
1901.09837 2019-01-29 cs.MA cs.LG 79%

Designing a Multi-Objective Reward Function for Creating Teams of Robotic Bodyguards Using Deep Reinforcement Learning

Hassam Ullah Sheikh, Ladislau Bölöni

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

Comments Accepted at the 1st Workshop on Goal Specifications for Reinforcement Learning at ICML 2018

详情

展开后加载摘要…

URL PDF HTML 收藏
1707.08817 2018-10-09 cs.AI 79%

Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards

Mel Vecerik, Todd Hester, Jonathan Scholz, Fumin Wang, Olivier Pietquin, Bilal Piot, Nicolas Heess, Thomas Rothörl, Thomas Lampe, Martin Riedmiller

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

详情

展开后加载摘要…

URL PDF HTML 收藏
1608.05742 2017-02-08 cs.RO 79%

Extending the OpenAI Gym for robotics: a toolkit for reinforcement learning using ROS and Gazebo

Iker Zamora, Nestor Gonzalez Lopez, Victor Mayoral Vilches, Alejandro Hernandez Cordero

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

详情

展开后加载摘要…

URL PDF HTML 收藏
1511.02889 2015-11-11 cs.AI 79%

A disembodied developmental robotic agent called Samu Bátfai

Norbert Bátfai

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

Comments 21 pages, 16 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.26646 2025-10-31 cs.RO cs.AI cs.LG 79%

Hybrid DQN-TD3 Reinforcement Learning for Autonomous Navigation in Dynamic Environments

Xiaoyi He, Danggui Chen, Zhenshuo Zhang, Zimeng Bai

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

Comments 6 pages, 5 figures; ROS+Gazebo (TurtleBot3) implementation; evaluation with PathBench metrics; code (primary): https://github.com/MayaCHEN-github/HierarchicalRL-robot-navigation; mirror (for reproducibility): https://github.com/ShowyHe/DRL-robot-navigation

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.07125 2024-03-13 eess.SY cs.SY 79%

Learning-Aided Control of Robotic Tether-Net with Maneuverable Nodes to Capture Large Space Debris

Achira Boonrath, Feng Liu, Elenora M. Botta, Souma Chowdhury

专题命中 模仿学习与强化学习 :robotic(title,abstract);robotics(comments)

Comments This paper was accepted for presentation in proceedings of IEEE International Conference on Robotics and Automation 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2006.06518 2021-06-08 eess.SY cs.SY 79%

Towards Expedited Impedance Tuning of a Robotic Prosthesis for Personalized Gait Assistance by Reinforcement Learning Control

Minhan Li, Yue Wen, Xiang Gao, Jennie Si, He Helen Huang

专题命中 模仿学习与强化学习 :robotic(title,abstract);robotics(journal_ref)

Journal ref IEEE Transactions on Robotics, 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
1712.05284 2018-06-04 nlin.AO cond-mat.dis-nn cond-mat.stat-mech cs.NE q-bio.NC 79%

Adaptation to criticality through organizational invariance in embodied agents

Miguel Aguilera, Manuel G. Bedia

专题命中 模仿学习与强化学习 :embodied agent(title,abstract)

Comments arXiv admin note: substantial text overlap with arXiv:1704.05255

Journal ref Aguilera, M., & Bedia, M. G. (2018). Adaptation to criticality through organizational invariance in embodied agents. Scientific reports, 8(1), 7723

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.22423 2026-08-04 cs.LG cs.CR cs.RO 版本更新 79%

ARMOR: Robust Reinforcement Learning-based Control for UAVs under Physical Attacks

ARMOR:面向无人机物理攻击的鲁棒强化学习控制

Pritam Dash, Ethan Chan, Nathan P. Lawrence, Karthik Pattabiraman

机构 * University of British Columbia(不列颠哥伦比亚大学) 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 :manipulation(abstract,abstract_cn);navigation(abstract);分类 cs.RO、cs.LG

AI总结 ARMOR是一种抗攻击的无模型强化学习控制器,通过两阶段训练框架学习鲁棒状态表示,可保障无人机在传感器受攻击时的安全运行,泛化能力更强且训练成本更低。

Comments Published at ICRA'2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.29613 2026-08-03 cs.RO cs.CL cs.CV 新提交 79%

WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning

WCM:用于视觉-语言-动作强化学习的世界评论者模型

Senyu Fei, Xiaopeng Yu, Siyin Wang, Xianzhong Zhao, Jingjing Gong, Xipeng Qiu

机构 * Tongji University(同济大学) Shanghai Innovation Institute(上海创新研究院) Fudan University(复旦大学)

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

AI总结 该研究针对视觉-语言-动作强化学习中评论者与机器人部分可观测性不匹配的问题,提出WCM模型,联合预测未来潜态与值估计,在149个仿真任务和7个真实任务上均实现最优性能与泛化性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.10369 2026-07-14 cs.RO cs.AI 新提交 79%

VINE: Taming Generative Control Policies for Reinforcement Learning

VINE:驯服强化学习中的生成控制策略

Rushuai Yang, Zhuo Han, Houlin Li, Hecheng Wang, Zhichao Wu, Rui Zhang, Zhaowei Zhang, Zihong Chen, Xiaohan Yan, Chiming Liu, Yi Chen, Wei Shan, Maoqing Yao

机构 * AgiBot(未知机构) The Hong Kong University of Science and Technology(香港科技大学) Peking University(北京大学)

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

AI总结 研究针对流匹配策略在值梯度强化学习中训练不稳定的问题,提出VINE方法。该方法通过在去噪步骤重建插值状态,创建稳定可微路径,实现稳定的端到端值梯度优化,在相关基准和任务中表现优于现有方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.27374 2026-06-26 cs.RO cs.CV 新提交 79%

World Action Models Enable Continual Imitation Learning with Recurrent Generative Replays

世界行动模型通过循环生成重放实现持续模仿学习

Manish Kumar Govind, Dominick Reilly, Smit Patel, Hieu Le, Srijan Das

机构 * University of North Carolina at Charlotte(北卡罗来纳大学夏洛特分校)

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

AI总结 提出循环生成重放(REGEN)框架,利用世界行动模型(WAM)生成伪重放轨迹,使机器人策略在不存储原始演示的情况下复习先前任务,在仿真和真实实验中减少50%灾难性遗忘,接近真实重放性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.14828 2026-06-11 cs.AI cs.RO 版本更新 79%

RoboGPT-R1: Enhancing Robot Task Planning with Reinforcement Learning

RoboGPT-R1: 通过强化学习增强机器人任务规划

Jinrui Liu, Bingyan Nie, Boyu Li, Yaran Chen, Yuze Wang, Shunsen He, Haoran Li

机构 * Institute of Automation, CASIA(中国科学院自动化研究所) School of Artificial Intelligence, UCAS(中国科学技术大学人工智能学院) Huawei Cloud Technology Co., Ltd(华为云技术有限公司)

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

AI总结 提出RoboGPT-R1两阶段微调框架,先监督学习获取基础知识,再通过强化学习提升视觉空间理解和推理能力,在EmbodiedBench上超越GPT-4o-mini 21.33%。

Journal ref Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026), pp. 2827-2837, IFAAMAS, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.02379 2026-05-08 cs.LG cs.CV 79%

Teaching Metric Distance to Discrete Autoregressive Language Models

向离散自回归语言模型传授度量距离

Jiwan Chung, Saejin Kim, Yongrae Jo, Jaewoo Park, Dongjun Min, Youngjae Yu

机构 * Yonsei University(延世大学) LG AI Research(LG AI研究院) Seoul National University(首尔国立大学)

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

AI总结 本文提出DIST2Loss,通过奖励加权分布替代one-hot目标,提升离散自回归模型的数据效率和跨领域表现,应用于视觉 grounding、机器人操控、奖励建模和向量量化图像生成。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.05595 2026-04-08 cs.RO cs.CV 79%

Uncovering Linguistic Fragility in Vision-Language-Action Models via Diversity-Aware Red Teaming

通过多样性感知的红队行动揭示视觉-语言-动作模型中的语言脆弱性

Baoshun Tong, Haoran He, Ling Pan, Yang Liu, Liang Lin

机构 * School of Computer Science and Engineering, Sun Yat-sen University(中山大学计算机科学与工程学院) The Hong Kong University of Science and Technology(香港科技大学)

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

AI总结 本文提出DAERT框架,通过评估统一策略生成多样化挑战性指令,揭示VLA模型在语言变化下的脆弱性,实验显示任务成功率从93.33%降至5.85%。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.16065 2026-03-24 cs.RO cs.AI 79%

Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models

大奖励模型:基于视觉-语言模型的通用在线机器人奖励生成

Yanru Wu, Weiduo Yuan, Ang Qi, Vitor Guizilini, Jiageng Mao, Yue Wang

机构 * USC Physical Superintelligence Lab(USC物理超智能实验室) Toyota Research Institute(丰田研究院)

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

AI总结 本文提出利用视觉-语言模型生成通用在线机器人奖励,通过零样本方式提升策略学习效率,实验显示在30次迭代内显著提高初始策略成功率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.15605 2025-12-02 cs.RO cs.CL cs.CV 79%

SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models

SRPO:用于视觉-语言-动作模型的自指政策优化

Senyu Fei, Siyin Wang, Li Ji, Ao Li, Shiduo Zhang, Liming Liu, Jinlong Hou, Jingjing Gong, Xianzhong Zhao, Xipeng Qiu

机构 * Fudan University(复旦大学) Tongji University(同济大学) Shanghai Innovation Institute(上海创新研究院)

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

AI总结 SRPO通过自指政策优化方法,利用模型自身生成的成功轨迹作为参考,有效解决VLA-RL中的奖励稀疏问题,实现高成功率和鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.18878 2025-11-25 cs.RO cs.AI 79%

Accelerating Reinforcement Learning via Error-Related Human Brain Signals

通过误差相关的人脑信号加速强化学习

Suzie Kim, Hye-Bin Shin, Hyo-Jeong Jang

机构 * Dept. of Artificial Intelligence Korea University Seoul, Republic of Korea(人工智能系韩国大学首尔共和国)

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

AI总结 通过整合误差相关的人脑信号,加速复杂机器人操作中的强化学习,提升任务成功率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.12737 2025-11-05 cs.LG cs.AI 79%

Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning

Hongjoon Ahn, Heewoong Choi, Jisu Han, Taesup Moon

机构 * Department of Electrical and Computer Engineering (ECE), Seoul National University(电子与计算机工程系,首尔国立大学) Interdisciplinary Program in Artificial Intelligence (IPAI), Seoul National University(人工智能跨学科项目,首尔国立大学) ASRI / INMC, Seoul National University(ASRI/INMC,首尔国立大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12392 2025-10-15 cs.RO cs.LG 79%

Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking

Junhyuk So, Chiwoong Lee, Shinyoung Lee, Jungseul Ok, Eunhyeok Park

机构 * Department of Computer Science & Engineering(计算机科学与工程系) Graduate School of Artificial Intelligence(人工智能研究生院) POSTECH

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

Comments Accepted at NeurIPS25

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.23308 2025-09-04 cond-mat.soft cs.LG cs.RO physics.bio-ph 79%

Reinforcement Learning for Active Matter

Wenjie Cai, Gongyi Wang, Yu Zhang, Xiang Qu, Zihan Huang

机构 * School of Physics and Electronics, Hunan University, Changsha 410082, China(物理与电子学院,湖南大学,长沙410082,中国) Department of Physics, King's College London, London WC2R 2LS, United Kingdom(物理系,伦敦国王学院,伦敦WC2R 2LS,英国)

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

Comments 16 pages, 8 figures

Journal ref Biophysics Rev. 2025, 6, 031302

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.14972 2025-07-08 cs.RO cs.LG 79%

MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning

Suning Huang, Zheyu Zhang, Tianhai Liang, Yihan Xu, Zhehao Kou, Chenhao Lu, Guowei Xu, Zhengrong Xue, Huazhe Xu

机构 * Tsinghua University(清华大学) Stanford University(斯坦福大学) University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

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

详情

展开后加载摘要…

URL PDF HTML 收藏