机器人 / 具身智能 - arXivDaily 专题

2202.01141 2022-09-13 cs.RO cs.LG 88%

Federated Reinforcement Learning for Collective Navigation of Robotic Swarms

Seongin Na, Tomáš Rouček, Jiří Ulrich, Jan Pikman, Tomáš Krajník, Barry Lennox, Farshad Arvin

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

Comments 10 pages, 8 figures, submitted to IEEE Transactions on Cognitive and Developmental Systems Journal (R1)

2111.02936 2021-11-05 cs.RO cs.LG 88%

Causal versus Marginal Shapley Values for Robotic Lever Manipulation Controlled using Deep Reinforcement Learning

Sindre Benjamin Remman, Inga Strümke, Anastasios M. Lekkas

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

Comments Submitted to the American Control Conference 2022

2003.13321 2020-04-08 cs.LG cs.RO stat.ML 88%

Ultrasound-Guided Robotic Navigation with Deep Reinforcement Learning

Hannes Hase, Mohammad Farid Azampour, Maria Tirindelli, Magdalini Paschali, Walter Simson, Emad Fatemizadeh, Nassir Navab

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

Comments Submitted for IROS 2020

2209.10149 2022-09-22 cs.RO 88%

Goal-Aware Generative Adversarial Imitation Learning from Imperfect Demonstration for Robotic Cloth Manipulation

Yoshihisa Tsurumine, Takamitsu Matsubara

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

Comments Accepted by Robotics and Autonomous Systems

2103.01434 2021-11-22 cs.RO 88%

Learning Robotic Manipulation Tasks via Task Progress based Gaussian Reward and Loss Adjusted Exploration

Sulabh Kumra, Shirin Josh, Ferat Sahin

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

Comments Accepted for publication in IEEE Robotics and Automation Letters (RA-L)

2102.04148 2021-02-09 cs.RO 88%

Deep Reinforcement Learning for the Control of Robotic Manipulation: A Focussed Mini-Review

Rongrong Liu, Florent Nageotte, Philippe Zanne, Michel de Mathelin, Birgitta Dresp-Langley

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

Journal ref Robotics, 2021, 10, 1, 22

2602.20715 2026-02-25 cs.RO 88%

IG-RFT: An Interaction-Guided RL Framework for VLA Models in Long-Horizon Robotic Manipulation

IG-RFT: 一种基于交互引导的强化学习框架用于长时域机器人操作中的VLA模型

Zhian Su, Weijie Kong, Haonan Dong, Huixu Dong

机构 * Grasp Laboratory, Mechanical Engineering Department, Zhejiang University（浙江大学机械工程学院抓取实验室）； Torch Kernel Co., Ltd.（火炬核科技有限公司）

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

AI总结 IG-RFT通过交互引导强化学习框架提升VLA模型在长时域机器人任务中的性能，实现85%的成功率，优于传统方法。

2512.23703 2025-12-30 cs.RO 88%

Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation

Robo-Dopamine：高精度机器人操作的通用过程奖励建模

Huajie Tan, Sixiang Chen, Yijie Xu, Zixiao Wang, Yuheng Ji, Cheng Chi, Yaoxu Lyu, Zhongxia Zhao, Xiansheng Chen, Peterson Co, Shaoxuan Xie, Guocai Yao, Pengwei Wang, Zhongyuan Wang, Shanghang Zhang

机构 * State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（1 多媒体信息处理国家重点实验室，计算机学院，北京大学）； Beijing Academy of Artificial Intelligence（2 北京人工智能研究院）； University of Sydney（3 新南威尔士大学）； Institute of Automation, Chinese Academy of Sciences（4 中国科学院自动化研究所）

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

AI总结 Robo-Dopamine通过多视角奖励融合和分步奖励离散化，提出了一种通用过程奖励模型，提升机器人操作的精准度和策略学习效率。

Comments 27 pages, 11 figures

2301.13450 2024-11-20 cs.RO 88%

Learning Vision-based Robotic Manipulation Tasks Sequentially in Offline Reinforcement Learning Settings

Sudhir Pratap Yadav, Rajendra Nagar, Suril V. Shah

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

Comments 7 pages, 5 Figures

Journal ref Robotica 42 (2024) 1715-1730

2409.14216 2024-09-24 cs.RO cs.AI cs.CV cs.LG 88%

R-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Models

Viet Dung Nguyen, Zhizhuo Yang, Christopher L. Buckley, Alexander Ororbia

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

Comments 20 pages, 2 algorithms, 2 tables, 5 figures, submitted to ICRA 2025

2306.03615 2024-06-06 cs.LG 88%

PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation

Runze Liu, Yali Du, Fengshuo Bai, Jiafei Lyu, Xiu Li

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

Comments Accepted to ICML 2024

2203.00141 2022-11-21 cs.RO 88%

GA+DDPG+HER: Genetic Algorithm-Based Function Optimizer in Deep Reinforcement Learning for Robotic Manipulation Tasks

Adarsh Sehgal, Nicholas Ward, Hung Manh La, Christos Papachristos, Sushil Louis

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

Comments This submission is replacement of: 2203.00141

2204.03656 2022-11-03 cs.RO 88%

Automatic Parameter Optimization Using Genetic Algorithm in Deep Reinforcement Learning for Robotic Manipulation Tasks

Adarsh Sehgal, Nicholas Ward, Hung La, Sushil Louis

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

Comments I want to replace previous submission by this new submission with same title

1710.03937 2019-02-05 cs.AI cs.LG cs.RO 88%

PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planning

Aleksandra Faust, Oscar Ramirez, Marek Fiser, Kenneth Oslund, Anthony Francis, James Davidson, Lydia Tapia

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

Comments 9 pages, 7 figures

Journal ref IEEE International Conference on Robotics and Automation (ICRA), 2018

2601.16985 2026-01-27 cs.RO cs.AI 88%

Breaking Task Impasses Quickly: Adaptive Neuro-Symbolic Learning for Open-World Robotics

快速突破任务瓶颈：面向开放世界机器人的自适应神经符号学习

Pierrick Lorang

机构 * Human-Robot Interaction Lab, Tufts University（塔夫茨大学人机交互实验室）

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

AI总结本文提出了一种自适应神经符号学习框架，通过整合符号学习与强化学习，提升机器人在开放世界中的快速适应能力与鲁棒性。

Comments IEEE ICRA 2025 Doctoral Consortium

2501.14942 2025-01-28 cs.RO cs.AI 88%

Force-Based Robotic Imitation Learning: A Two-Phase Approach for Construction Assembly Tasks

Hengxu You, Yang Ye, Tianyu Zhou, Jing Du

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

Comments 36 pages

2312.02976 2024-08-09 cs.RO cs.AI cs.CV 88%

SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World

Kiana Ehsani, Tanmay Gupta, Rose Hendrix, Jordi Salvador, Luca Weihs, Kuo-Hao Zeng, Kunal Pratap Singh, Yejin Kim, Winson Han, Alvaro Herrasti, Ranjay Krishna, Dustin Schwenk, Eli VanderBilt, Aniruddha Kembhavi

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

Comments First six authors contributed equally. Project page: https://spoc-robot.github.io/

2401.17032 2024-06-21 cs.RO cs.CV cs.LG 88%

M2CURL: Sample-Efficient Multimodal Reinforcement Learning via Self-Supervised Representation Learning for Robotic Manipulation

Fotios Lygerakis, Vedant Dave, Elmar Rueckert

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

Comments Project website: https://sites.google.com/view/M2CURL/home

1905.13402 2020-05-19 cs.LG cs.AI cs.RO stat.ML 88%

Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks

Brijen Thananjeyan, Ashwin Balakrishna, Ugo Rosolia, Felix Li, Rowan McAllister, Joseph E. Gonzalez, Sergey Levine, Francesco Borrelli, Ken Goldberg

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

Comments Robotics and Automation Letters and International Conference on Robotics and Automation 2020. First two authors contributed equally

Journal ref Robotics and Automation Letters 2020

2206.14244 2023-05-30 cs.RO cs.AI cs.CV cs.LG 87%

Masked World Models for Visual Control

Younggyo Seo, Danijar Hafner, Hao Liu, Fangchen Liu, Stephen James, Kimin Lee, Pieter Abbeel

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

Comments Project website: https://sites.google.com/view/mwm-rl. Accepted to CoRL 2022

2008.07792 2021-03-29 cs.AI cs.CV cs.LG cs.RO 87%

ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation

Fei Xia, Chengshu Li, Roberto Martín-Martín, Or Litany, Alexander Toshev, Silvio Savarese

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

Comments First two authors contributed equally. Access project website at http://svl.stanford.edu/projects/relmogen

1812.00568 2018-12-04 cs.RO cs.AI cs.CV cs.LG 87%

Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control

Frederik Ebert, Chelsea Finn, Sudeep Dasari, Annie Xie, Alex Lee, 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.AI、cs.CV

2606.18594 2026-06-18 cs.RO cs.AI 新提交 87%

Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation

基于视觉的机器人操作中强化学习动作空间的基准测试

Seyed Alireza Azimi, Homayoon Farrahi, Abhishek Naik, Colin Bellinger, A. Rupam Mahmood

机构 * Department of Computing Science, University of Alberta（阿尔伯塔大学计算机科学系）； National Research Council Canada（加拿大国家研究委员会）； School of Electrical Engineering and Computer Science, University of Ottawa（渥太华大学电气工程与计算机科学学院）； Vector Institute（向量研究所）； Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究所）

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

AI总结本研究通过模拟到现实的迁移，在物体抓取和推动任务中评估了四种动作空间，发现关节速度动作空间在平滑性和任务性能上最优，并为RL实践者提供了动作空间选择指导。

Comments 9 pages with references

2512.03556 2025-12-04 cs.RO cs.CV 87%

RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RL

RoboScape-R: 通用机器人训练的统一奖励-观测世界模型

Yinzhou Tang, Yu Shang, Yinuo Chen, Bingwen Wei, Xin Zhang, Shu'ang Yu, Liangzhi Shi, Chao Yu, Chen Gao, Wei Wu, Yong Li

机构 * Tsinghua University（清华大学）； Manifold AI

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

AI总结 RoboScape-R通过统一奖励-观测世界模型提升机器人训练的泛化能力，实现37.5%的性能提升。

2209.14271 2025-06-17 cs.RO cs.LG 87%

Generalization in Deep Reinforcement Learning for Robotic Navigation by Reward Shaping

Victor R. F. Miranda, Armando A. Neto, Gustavo M. Freitas, Leonardo A. Mozelli

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

Comments IEEE Transactions on Industrial Electronics (2023)

Journal ref IEEE Transactions on Industrial Electronics, vol. 71, no. 6, pp. 6013-6020, (2024)

2311.12854 2023-11-23 cs.AI cs.RO 87%

Enhancing Robotic Manipulation: Harnessing the Power of Multi-Task Reinforcement Learning and Single Life Reinforcement Learning in Meta-World

Ghadi Nehme, Ishan Sabane, Tejas Y. Deo

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

2204.13906 2022-10-13 cs.RO cs.LG 87%

Unsupervised Reinforcement Learning for Transferable Manipulation Skill Discovery

Daesol Cho, Jigang Kim, H. Jin Kim

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

Comments 8 pages, 9 figures; accepted for publication in the IEEE Robotics and Automation Letters (RA-L); supplementary video available at https://www.youtube.com/watch?v=bF3Y4WXfM7c&t=9s

Journal ref IEEE Robotics and Automation Letters 7 (2022) 7455-7462

1909.12200 2020-06-05 cs.RO cs.LG 87%

Scaling data-driven robotics with reward sketching and batch reinforcement learning

Serkan Cabi, Sergio Gómez Colmenarejo, Alexander Novikov, Ksenia Konyushkova, Scott Reed, Rae Jeong, Konrad Zolna, Yusuf Aytar, David Budden, Mel Vecerik, Oleg Sushkov, David Barker, Jonathan Scholz, Misha Denil, Nando de Freitas, Ziyu Wang

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

Comments Project website: https://sites.google.com/view/data-driven-robotics/

Journal ref Robotics: Science and Systems Conference 2020

2604.00055 2026-04-02 cs.RO cs.CV cs.LG 87%

Generalizable Dense Reward for Long-Horizon Robotic Tasks

可泛化的密集奖励用于长周期机器人任务

Silong Yong, Stephen Sheng, Carl Qi, Xiaojie Wang, Evan Sheehan, Anurag Shivaprasad, Yaqi Xie, Katia Sycara, Yesh Dattatreya

机构 * Carnegie Mellon University（卡内基梅隆大学）； Amazon Robotics（亚马逊机器人）； UT Austin（德克萨斯大学奥斯汀分校）

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

AI总结本文提出VLLR框架，结合外部奖励和内部奖励提升长周期机器人任务性能，通过任务分解和自信心引导实现无需人工奖励工程的高效训练。

Comments Project page: https://silongyong.github.io/vllr_project_page/

2412.20977 2025-08-13 cs.AI cs.CV cs.RO 87%

UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI

Fangwei Zhong, Kui Wu, Churan Wang, Hao Chen, Hai Ci, Zhoujun Li, Yizhou Wang

机构 * School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）； State Key Laboratory of Complex & Critical Software Environment, Beihang University（北航复杂与关键软件环境国家重点实验室）； School of Computer Science, Institute for Artificial Intelligence, State Key Laboratory of General Artificial Intelligence, Peking University（北京大学计算机学院）； City University of Macau（澳门城市大学）； National University of Singapore（新加坡国立大学）； Beijing Institute for General Artificial Intelligence (BIGAI)（北京通用人工智能研究院）

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

Comments ICCV 2025 (Highlight), Project page: http://unrealzoo.site/

1. 模仿学习与强化学习 4103 篇

Federated Reinforcement Learning for Collective Navigation of Robotic Swarms

Causal versus Marginal Shapley Values for Robotic Lever Manipulation Controlled using Deep Reinforcement Learning

Ultrasound-Guided Robotic Navigation with Deep Reinforcement Learning

Goal-Aware Generative Adversarial Imitation Learning from Imperfect Demonstration for Robotic Cloth Manipulation

Learning Robotic Manipulation Tasks via Task Progress based Gaussian Reward and Loss Adjusted Exploration

Deep Reinforcement Learning for the Control of Robotic Manipulation: A Focussed Mini-Review

IG-RFT: An Interaction-Guided RL Framework for VLA Models in Long-Horizon Robotic Manipulation

Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation

Learning Vision-based Robotic Manipulation Tasks Sequentially in Offline Reinforcement Learning Settings

R-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Models

PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation

GA+DDPG+HER: Genetic Algorithm-Based Function Optimizer in Deep Reinforcement Learning for Robotic Manipulation Tasks

Automatic Parameter Optimization Using Genetic Algorithm in Deep Reinforcement Learning for Robotic Manipulation Tasks

PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planning

Breaking Task Impasses Quickly: Adaptive Neuro-Symbolic Learning for Open-World Robotics

Force-Based Robotic Imitation Learning: A Two-Phase Approach for Construction Assembly Tasks

SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World

M2CURL: Sample-Efficient Multimodal Reinforcement Learning via Self-Supervised Representation Learning for Robotic Manipulation

Safety Augmented Value Estimation from Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks

Masked World Models for Visual Control

ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation

Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control

Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation

RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RL

Generalization in Deep Reinforcement Learning for Robotic Navigation by Reward Shaping

Enhancing Robotic Manipulation: Harnessing the Power of Multi-Task Reinforcement Learning and Single Life Reinforcement Learning in Meta-World

Unsupervised Reinforcement Learning for Transferable Manipulation Skill Discovery

Scaling data-driven robotics with reward sketching and batch reinforcement learning

Generalizable Dense Reward for Long-Horizon Robotic Tasks

UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI