机器人 / 具身智能 - arXivDaily 专题

2410.11448 2024-10-25 cs.LG 80%

Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement

Zhi Wang, Li Zhang, Wenhao Wu, Yuanheng Zhu, Dongbin Zhao, Chunlin Chen

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

Comments NeurIPS 2024. TLDR: We leverage the sequential modeling ability of the transformer architecture and robust task representation learning via world model disentanglement to achieve efficient generalization in offline meta-RL

2402.11799 2024-03-08 cs.RO 80%

Decentralized Multi-Robot Navigation for Autonomous Surface Vehicles with Distributional Reinforcement Learning

Xi Lin, Yewei Huang, Fanfei Chen, Brendan Englot

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

Comments The 2024 IEEE International Conference on Robotics and Automation (ICRA 2024)

1912.04078 2022-05-10 cs.RO 80%

Reinforcement Learning-based Visual Navigation with Information-Theoretic Regularization

Qiaoyun Wu, Kai Xu, Jun Wang, Mingliang Xu, Xiaoxi Gong, Dinesh Manocha

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

Comments corresponding author: Kai Xu (kevin.kai.xu@gmail.com) and Jun Wang (wjun@nuaa.edu.cn), accepted by IEEE Robotics and Automation Letters

2101.05325 2021-11-05 cs.RO 80%

Learning Kinematic Feasibility for Mobile Manipulation through Deep Reinforcement Learning

Daniel Honerkamp, Tim Welschehold, Abhinav Valada

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

Comments Accepted for publication in RA-L. Code and Models: http://rl.uni-freiburg.de/research/kinematic-feasibility-rl

Journal ref IEEE Robotics and Automation Letters (RA-L), vol. 6, no. 4, pp. 6289-6296, 2021

2103.12883 2021-03-30 cs.RO 80%

Deep Reinforcement Learning for Mapless Navigation of a Hybrid Aerial Underwater Vehicle with Medium Transition

Ricardo Bedin Grando, Junior Costa de Jesus, Victor Augusto Kich, Alisson Henrique Kolling, Nicolas Pieper Bortoluzzi, Pedro Miranda Pinheiro, Armando Alves Neto, Paulo Lilles Jorge Drews-Jr

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

Comments Accepted to the IEEE International Conference on Robotics and Automation (ICRA) 2021

2004.10886 2020-09-29 cs.RO 80%

Stability-Guaranteed Reinforcement Learning for Contact-rich Manipulation

Shahbaz A. Khader, Hang Yin, Pietro Falco, Danica Kragic

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

Comments Accepted at Robotics and Automation Letters

1910.14475 2020-03-06 cs.RO 80%

Dynamic Cloth Manipulation with Deep Reinforcement Learning

Rishabh Jangir, Guillem Alenya, Carme Torras

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

Comments 6 pages, 5 figures, accepted at International Conference on Robotics and Automation ICRA'2020

2605.14937 2026-05-15 cs.LG cs.AI cs.RO 80%

Slot-MPC: Goal-Conditioned Model Predictive Control with Object-Centric Representations

Slot-MPC：基于目标中心表示的面向目标的模型预测控制

Jonathan Spieler, Angel Villar-Corrales, Sven Behnke

机构 * Autonomous Intelligent Systems（自主智能系统）； Computer Science Institute VI（计算机科学研究所VI）； Intelligent Systems and Robotics（智能系统与机器人）； Center for Robotics（机器人中心）； Lamarr Institute for Machine Learning and Artificial Intelligence（拉马尔人工智能学习与智能研究所）； University of Bonn, Germany（波恩大学，德国）

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.AI、cs.LG

AI总结 Slot-MPC通过模型预测控制实现目标中心表示的规划，利用可微分的世界模型提升任务性能和规划效率，优于非目标中心世界模型基线。

2604.27472 2026-05-01 cs.AI cs.LG cs.RO 80%

PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations

PRTS：通过对比表示实现的原始推理与任务系统

Yang Zhang, Jiangyuan Zhao, Chenyou Fan, Fangzheng Yan, Tian Li, Haitong Tang, Sen Fu, Xuan'er Wu, Qizhen Weng, Weinan Zhang, Xiu Li, Chi Zhang, Chenjia Bai, Xuelong Li

机构 * Institute of Artificial Intelligence (TeleAI), China Telecom（人工智能研究院（TeleAI），中国电信）； Tsinghua University（清华大学）； Shanghai Jiao Tong University（上海交通大学）； Fudan University（复旦大学）

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、cs.LG

AI总结 PRTS通过目标引导强化学习重构预训练过程，学习统一嵌入空间以评估物理可行性，提升机器人任务执行与长期规划能力。

Comments 38 pages, 12 figures

2507.06625 2026-03-05 cs.RO cs.AI cs.LG 80%

Q-Guided Stein Variational Model Predictive Control via RL-informed Policy Prior

基于RL引导的Stein变分模型预测控制的Q引导方法

Shizhe Cai, Zeya Yin, Jayadeep Jacob, Fabio Ramos

机构 * University of Sydney（悉尼大学）； NVIDIA（英伟达）

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、cs.LG

AI总结 Q-SVMPC通过结合RL引导的策略先验和Stein变分方法，提升轨迹优化的样本效率、稳定性和鲁棒性。

Comments 8 pages, 6 figures

2512.16911 2025-12-19 cs.LG cs.AI cs.RO 80%

Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning

后验行为克隆：为高效强化学习微调预训练BC策略

Andrew Wagenmaker, Perry Dong, Raymond Tsao, Chelsea Finn, Sergey Levine

机构 * UC Berkeley（伯克利大学）； Stanford（斯坦福大学）

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

AI总结本文提出后验行为克隆策略，通过建模示范者行为的后验分布来提升强化学习微调效果。

2510.00225 2025-10-02 cs.RO cs.AI cs.LG cs.LO 80%

TGPO: Temporal Grounded Policy Optimization for Signal Temporal Logic Tasks

Yue Meng, Fei Chen, Chuchu Fan

机构 * Massachusetts Institute of Technology（麻省理工学院）

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

2407.10341 2025-07-29 cs.RO cs.AI cs.LG 80%

Affordance-Guided Reinforcement Learning via Visual Prompting

Olivia Y. Lee, Annie Xie, Kuan Fang, Karl Pertsch, Chelsea Finn

机构 * Stanford University（斯坦福大学）； Cornell University（康奈尔大学）； 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：robotics(abstract)；manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments 8 pages, 6 figures. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2025

2505.06482 2025-05-20 cs.LG cs.AI cs.RO 80%

Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach

Minting Pan, Yitao Zheng, Jiajian Li, Yunbo Wang, Xiaokang Yang

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.AI、cs.LG

2501.17842 2025-01-30 cs.LG cs.AI cs.RO 80%

From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learning

Junseok Park, Hyeonseo Yang, Min Whoo Lee, Won-Seok Choi, Minsu Lee, Byoung-Tak Zhang

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、cs.LG

Comments Extended version of AAAI 2024 paper: Unveiling the Significance of Toddler-Inspired Reward Transition in Goal-Oriented Reinforcement Learning. This manuscript is currently being prepared for journal submission

2310.19424 2023-10-31 cs.LG cs.AI cs.RO 80%

Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills

Seongun Kim, Kyowoon Lee, Jaesik Choi

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、cs.LG

Comments ICML 2023. First two authors contributed equally. Code at https://github.com/seongun-kim/vcrl

2307.02889 2023-07-11 cs.RO cs.AI cs.LG 80%

Learning to Solve Tasks with Exploring Prior Behaviours

Ruiqi Zhu, Siyuan Li, Tianhong Dai, Chongjie Zhang, Oya Celiktutan

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、cs.LG

2207.09243 2023-03-10 cs.RO cs.AI cs.LG 80%

Abstract Demonstrations and Adaptive Exploration for Efficient and Stable Multi-step Sparse Reward Reinforcement Learning

Xintong Yang, Ze Ji, Jing Wu, Yu-kun Lai

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

Comments Accepted by The 27th IEEE International Conference on Automation and Computing (ICAC2022)

Journal ref 2022 27th International Conference on Automation and Computing (ICAC), Bristol, United Kingdom, 2022, pp. 1-6

2301.11741 2023-02-21 cs.LG cs.AI cs.RO 80%

Outcome-directed Reinforcement Learning by Uncertainty & Temporal Distance-Aware Curriculum Goal Generation

Daesol Cho, Seungjae Lee, H. Jin Kim

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、cs.LG

Comments ICLR 2023 Spotlight. First two authors contributed equally

2208.08133 2023-01-23 cs.LG cs.AI cs.RO 80%

Metric Residual Networks for Sample Efficient Goal-Conditioned Reinforcement Learning

Bo Liu, Yihao Feng, Qiang Liu, Peter Stone

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

Comments Goal-conditioned reinforcement learning, neural architecture design

2202.01741 2022-07-11 cs.LG cs.AI cs.RO 80%

How to Leverage Unlabeled Data in Offline Reinforcement Learning

Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Karol Hausman, Chelsea Finn, Sergey Levine

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、cs.LG

Comments ICML 2022

2109.08128 2021-09-17 cs.LG cs.AI cs.RO 80%

Conservative Data Sharing for Multi-Task Offline Reinforcement Learning

Tianhe Yu, Aviral Kumar, Yevgen Chebotar, Karol Hausman, Sergey Levine, Chelsea Finn

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、cs.LG

2005.07648 2021-07-09 cs.RO cs.AI cs.CL cs.CV 80%

Language Conditioned Imitation Learning over Unstructured Data

Corey Lynch, Pierre Sermanet

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

Comments Published at RSS 2021

2006.15807 2020-12-15 cs.RO cs.AI cs.LG cs.MA 80%

Using Reinforcement Learning to Herd a Robotic Swarm to a Target Distribution

Zahi M. Kakish, Karthik Elamvazhuthi, Spring Berman

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

Comments Paper was submitted to Conference on Robot Learning 2019 and IEEE Robotics and Automation Letters 2020 Revised, updated, and submitted to DARS/SWARMS 2021

2011.13885 2020-11-30 cs.LG cs.AI cs.RO stat.ML 80%

Offline Learning from Demonstrations and Unlabeled Experience

Konrad Zolna, Alexander Novikov, Ksenia Konyushkova, Caglar Gulcehre, Ziyu Wang, Yusuf Aytar, Misha Denil, Nando de Freitas, Scott Reed

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、cs.LG

Comments Accepted to Offline Reinforcement Learning Workshop at Neural Information Processing Systems (2020)

2002.02667 2020-05-22 cs.LG cs.AI cs.RO eess.SP 80%

Automated Lane Change Strategy using Proximal Policy Optimization-based Deep Reinforcement Learning

Fei Ye, Xuxin Cheng, Pin Wang, Ching-Yao Chan, Jiucai Zhang

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、cs.LG

2102.02915 2021-02-08 cs.RO cs.LG 80%

How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned

Julian Ibarz, Jie Tan, Chelsea Finn, Mrinal Kalakrishnan, Peter Pastor, Sergey Levine

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

Journal ref Journal of Robotics Research (IJRR), February 2021

2608.11350 2026-08-13 cs.CL cs.RO 新提交 79%

Self-Evolving Embodied Agents via Skill-Harness Evolution

基于技能-工具链进化的自演化具身智能体

Peidong Wang, Zhiming Ma, Ying Chang, Xufang Luo, Xiaocui Yang, Shi Feng, Yuqing Yang, Dongsheng Li

机构 * Microsoft Research（微软研究院）； Northeastern University（东北大学）

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

AI总结提出免训练的SHAPER框架，通过演化技能与工具链实现冻结模型驱动的自演化具身智能体，在VLABench等数据集上验证其适配优势。

2608.02953 2026-08-11 cs.CV 版本更新 79%

RealWeather: Realistic and Scene-Faithful Weather Translation with Driving World Models

RealWeather：基于驾驶世界模型的逼真且场景忠实的天气转换

Yuwei Ning, Liangzhi Wang, Yi Xiao, Zhenhua Wu, Yun Pang, Mingkun Chang, Jichang Li, Guanbin Li

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

AI总结 RealWeather是一种驾驶世界模型，通过渐进式逼真度引导和场景忠实度强化学习优化实现逼真且场景忠实的天气转换，在视觉逼真度、结构保留等方面优于现有方法，支持长尾天气场景生成与零样本泛化。

Comments Under submission

2603.13888 2026-08-05 cs.RO 版本更新 79%

Path-conditioned Reinforcement Learning-based Local Planning for Long-Range Navigation

基于路径条件的强化学习局部规划用于远距离导航

Mateo Haro, Julia Richter, Fan Yang, Cesar Cadena, Marco Hutter

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

AI总结本文提出一种基于强化学习的局部导航策略，利用路径信息作为上下文指导，提升远距离导航效率并保持在路径信息退化时的鲁棒性。

1. 模仿学习与强化学习 4106 篇

Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement

Decentralized Multi-Robot Navigation for Autonomous Surface Vehicles with Distributional Reinforcement Learning

Reinforcement Learning-based Visual Navigation with Information-Theoretic Regularization

Learning Kinematic Feasibility for Mobile Manipulation through Deep Reinforcement Learning

Deep Reinforcement Learning for Mapless Navigation of a Hybrid Aerial Underwater Vehicle with Medium Transition

Stability-Guaranteed Reinforcement Learning for Contact-rich Manipulation

Dynamic Cloth Manipulation with Deep Reinforcement Learning

Slot-MPC: Goal-Conditioned Model Predictive Control with Object-Centric Representations

PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations

Q-Guided Stein Variational Model Predictive Control via RL-informed Policy Prior

Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning

TGPO: Temporal Grounded Policy Optimization for Signal Temporal Logic Tasks

Affordance-Guided Reinforcement Learning via Visual Prompting

Video-Enhanced Offline Reinforcement Learning: A Model-Based Approach

From Sparse to Dense: Toddler-inspired Reward Transition in Goal-Oriented Reinforcement Learning

Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills

Learning to Solve Tasks with Exploring Prior Behaviours

Abstract Demonstrations and Adaptive Exploration for Efficient and Stable Multi-step Sparse Reward Reinforcement Learning

Outcome-directed Reinforcement Learning by Uncertainty & Temporal Distance-Aware Curriculum Goal Generation

Metric Residual Networks for Sample Efficient Goal-Conditioned Reinforcement Learning

How to Leverage Unlabeled Data in Offline Reinforcement Learning

Conservative Data Sharing for Multi-Task Offline Reinforcement Learning

Language Conditioned Imitation Learning over Unstructured Data

Using Reinforcement Learning to Herd a Robotic Swarm to a Target Distribution

Offline Learning from Demonstrations and Unlabeled Experience

Automated Lane Change Strategy using Proximal Policy Optimization-based Deep Reinforcement Learning

How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned

Self-Evolving Embodied Agents via Skill-Harness Evolution

RealWeather: Realistic and Scene-Faithful Weather Translation with Driving World Models

Path-conditioned Reinforcement Learning-based Local Planning for Long-Range Navigation