机器人 / 具身智能

On the Dual-Use Dilemma in Physical Reasoning and Force

William Xie, Enora Rice, Nikolaus Correll

机构 * University of Colorado Boulder（科罗拉多大学博尔德分校） 纠错

专题命中 机器人学习 ：robot learning(abstract)；manipulation(abstract)；robotic(abstract)；分类 cs.RO

PlayFusion: Skill Acquisition via Diffusion from Language-Annotated Play

Lili Chen, Shikhar Bahl, Deepak Pathak

专题命中 机器人学习 ：robotics(abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.CV

Comments In CoRL 2023. Website at https://play-fusion.github.io

Teaching contact-rich tasks from visual demonstrations by constraint extraction

Christian Hegeler, Filippo Rozzi, Loris Roveda, Kevin Haninger

专题命中 机器人学习 ：manipulation(abstract)；robot policy(abstract)；robotic(abstract)；分类 cs.RO

Comments Submitted ICRA23. Code available at https://github.com/khaninger/contact_monitoring Video available at https://www.youtube.com/watch?v=Tf-zt8VKu_M

Visuomotor Control in Multi-Object Scenes Using Object-Aware Representations

Negin Heravi, Ayzaan Wahid, Corey Lynch, Pete Florence, Travis Armstrong, Jonathan Tompson, Pierre Sermanet, Jeannette Bohg, Debidatta Dwibedi

专题命中 机器人学习 ：robotics(abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.CV

Human-to-Robot Imitation in the Wild

Shikhar Bahl, Abhinav Gupta, Deepak Pathak

专题命中 机器人学习 ：robot learning(abstract)；manipulation(abstract)；分类 cs.RO、cs.AI、cs.CV

Comments Published at RSS 2022. Demos at https://human2robot.github.io

Generating Shared Latent Variables for Robots to Imitate Human Movements and Understand their Physical Limitations

Maxime Devanne, Sao Mai Nguyen

专题命中 机器人学习 ：robotics(abstract)；robot learning(abstract)；分类 cs.RO、cs.AI、cs.CV

Journal ref Leal-Taix{é} L; Roth S. Lecture Notes in Computer Science, 11130, Springer, Cham, pp.190-197, 2019, Computer Vision -- ECCV 2018 Workshops

Credit Assignment Safety Learning from Human Demonstrations

Ahalya Prabhakar, Aude Billard

专题命中 机器人学习 ：robotics(abstract)；robot learning(abstract)；navigation(abstract)；分类 cs.RO

Comments Presented at AI-HRI symposium as part of AAAI-FSS 2021 (arXiv:2109.10836)

Policy learning in SE(3) action spaces

Dian Wang, Colin Kohler, Robert Platt

专题命中 机器人学习 ：robotics(abstract)；manipulation(abstract)；robotic(abstract)；分类 cs.RO

Comments 17 pages, accepted at CoRL 2020

Practical Robot Learning from Demonstrations using Deep End-to-End Training

Akansel Cosgun, Thomas Rowntree, Ian Reid, Tom Drummond

专题命中 机器人学习 ：robot learning(title)；分类 cs.RO；manipulation(comments)；robotic(comments)

Comments Presented in RSS 2019 Workshop: "Emerging paradigms for robotic manipulation: from the lab to the productive world"

Multiform Adaptive Robot Skill Learning from Humans

Leidi Zhao, Raheem Lawhorn, Siddharth Patil, Steve Susanibar, Lu Lu, Cong Wang, Bo Ouyang

专题命中 机器人学习 ：robot learning(abstract)；manipulation(abstract)；robotic(abstract)；分类 cs.RO

Comments Accepted to 2017 Dynamic Systems and Control Conference (DSCC), Tysons Corner, VA, October 11-13

Learning Robot Activities from First-Person Human Videos Using Convolutional Future Regression

Jangwon Lee, Michael S. Ryoo

专题命中 机器人学习 ：robot learning(abstract)；manipulation(abstract)；分类 cs.RO、cs.AI、cs.CV

Deep Visual Foresight for Planning Robot Motion

Chelsea Finn, Sergey Levine

专题命中 机器人学习 ：robot learning(abstract)；manipulation(abstract)；分类 cs.RO、cs.AI、cs.CV

Comments ICRA 2017. Supplementary video: https://sites.google.com/site/robotforesight/

Learning Novel Skills from Language-Generated Demonstrations

Ao-Qun Jin, Tian-Yu Xiang, Xiao-Hu Zhou, Mei-Jiang Gui, Xiao-Liang Xie, Shi-Qi Liu, Shuang-Yi Wang, Yue Cao, Sheng-Bin Duan, Fu-Chao Xie, Zeng-Guang Hou

机构 * Institute of Automation Chinese Academy of Sciences（自动化研究所，中国科学院） 纠错

专题命中 机器人学习 ：robot learning(abstract,comments)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments 10 pages, International Conference on Learning Representations (ICLR) 2025 Workshop on Generative Models for Robot Learning (GenBot)

Positive-Unlabeled Constraint Learning for Inferring Nonlinear Continuous Constraints Functions from Expert Demonstrations

Baiyu Peng, Aude Billard

专题命中 机器人学习 ：robotics(abstract,journal_ref)；robotic(abstract)；分类 cs.RO、cs.AI、cs.LG

Journal ref IEEE Robotics and Automation Letters, vol. 10, no. 2, pp. 1593-1600, Feb. 2025

Max-Q Selective Imitation for Human-in-the-Loop Online Robot Learning

面向人在回路在线机器人学习的Max-Q选择性模仿

Zihang Wang, Yishan Wang

专题命中 机器人学习 ：robot learning(title)；分类 cs.RO、cs.AI

AI总结 本文提出Max-Q选择性模仿方法，结合MC Q-chunk评论家，在真实机器人USB抓取插入等任务中，训练效率显著优于HIL-SERL等基线方法。

Beyond Predefined Learning Objects: A Thinking-Learning Interaction Model for Up-to-Date Autonomous Robot Learning

超越预定义学习对象：面向最新自主机器人学习的思维-学习交互模型

Hong Su

机构 * School of Computer Science, Chengdu University of Information Technology（成都信息科技大学计算机学院） 纠错

专题命中 机器人学习 ：robot learning(title)；分类 cs.RO、cs.AI

AI总结 针对自主机器人在开放环境中无法依赖预定义学习对象的问题，提出一种思维-学习交互模型，通过思维指导学习（识别变化、选择证据、组织训练、规划验证）和学习促进思维（更新知识、经验、策略、推理）的双向机制，实现输入特征发现、输出类别扩展、模型更新和动作例程重构，实验验证了模型在特征适应、新类别形成、模型更新和动作优化上的有效性。

Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining

通过分离前向和逆向动力学预训练实现解耦的机器人学习

Wenyao Zhang, Bozhou Zhang, Zekun Qi, Wenjun Zeng, Xin Jin, Li Zhang

机构 * Shanghai Jiao Tong University（上海交通大学） ； Fudan University（复旦大学） ； Eastern Institute of Technology, Ningbo（宁波东部技术研究所） ； Shanghai Innovation Institute（上海创新研究院） ； Tsinghua University（清华大学） 纠错

专题命中 机器人学习 ：robot learning(title)；分类 cs.RO、cs.CV

AI总结 本文提出DeFI框架，通过分离前向和逆向动力学预训练，利用不同数据源解决视觉-动作耦合问题，实现端到端微调，实验表明在CALVIN ABC-D和SimplerEnv上取得最佳性能。

Comments ICLR 2026

QUART-Online: Latency-Free Large Multimodal Language Model for Quadruped Robot Learning

Xinyang Tong, Pengxiang Ding, Yiguo Fan, Donglin Wang, Wenjie Zhang, Can Cui, Mingyang Sun, Han Zhao, Hongyin Zhang, Yonghao Dang, Siteng Huang, Shangke Lyu

机构 * MiLAB, Westlake University, Hangzhou, 310030, China（西交利物浦大学微实验室，杭州，310030，中国） ； Zhejiang University, Hangzhou, 310027, China（浙江大学，杭州，310027，中国） ； Beijing University of Posts and Telecommunications, Beijing, 100876, China（北京邮电大学，北京，100876，中国） 纠错

专题命中 机器人学习 ：robot learning(title)；分类 cs.RO、cs.CV

Comments Accepted to ICRA 2025; Github page: https://quart-online.github.io

Autonomous Improvement of Instruction Following Skills via Foundation Models

Zhiyuan Zhou, Pranav Atreya, Abraham Lee, Homer Walke, Oier Mees, Sergey Levine

专题命中 机器人学习 ：robot learning(abstract,comments)；robot policy(abstract)；分类 cs.RO、cs.AI

Comments 2024 Conference on Robot Learning (CoRL)

Journal ref Conference on Robot Learning 2024

Quality Diversity for Robot Learning: Limitations and Future Directions

Sumeet Batra, Bryon Tjanaka, Stefanos Nikolaidis, Gaurav Sukhatme

专题命中 机器人学习 ：robot learning(title)；分类 cs.RO、cs.AI

Comments Accepted to GECCO 2024

Topology-Matching Normalizing Flows for Out-of-Distribution Detection in Robot Learning

Jianxiang Feng, Jongseok Lee, Simon Geisler, Stephan Gunnemann, Rudolph Triebel

专题命中 机器人学习 ：robot learning(title)；分类 cs.RO、cs.LG

Comments Accepted on CoRL2023

Task-Driven Detection of Distribution Shifts with Statistical Guarantees for Robot Learning

Alec Farid, Sushant Veer, Divyanshu Pachisia, Anirudha Majumdar

专题命中 机器人学习 ：robot learning(title)；分类 cs.RO、cs.LG

Towards a Grounded Theory of Causation for Embodied AI

Taco Cohen

专题命中 机器人学习 ：embodied AI(title)；分类 cs.AI、cs.LG

Journal ref Causal Representation Learning workshop at the 38th Conference on Uncertainty in Artificial Intelligence (UAI CRL 2022)

Imitation and Supervised Learning of Compliance for Robotic Assembly

Devesh K. Jha, Diego Romeres, William Yerazunis, Daniel Nikovski

专题命中 机器人学习 ：robotic(title)；分类 cs.RO、cs.AI

Comments 8 pages, 7 figures

A Study on Dense and Sparse (Visual) Rewards in Robot Policy Learning

Abdalkarim Mohtasib, Gerhard Neumann, Heriberto Cuayahuitl

专题命中 机器人学习 ：robot policy(title)；分类 cs.RO、cs.LG

Learning from demonstration using products of experts: applications to manipulation and task prioritization

Emmanuel Pignat, João Silvério, Sylvain Calinon

专题命中 机器人学习 ：manipulation(title)；分类 cs.RO、cs.LG

Unified Motion-Action Modeling for Heterogeneous Robot Learning

统一运动-动作建模用于异构机器人学习

Yunhao Cao, Shitong Liu, Chao Feng, Meryl Zhang, Xuanchen Lu, Andrew Owens, Kuan Fang

机构 * Cornell University（康奈尔大学） 纠错

专题命中 机器人学习 ：robot learning(title)；分类 cs.RO；manipulation(comments)

AI总结 提出UMA模型，利用3D物体运动轨迹作为共享接口，通过掩码生成目标统一视觉运动控制和动力学建模，实现跨异构数据源的多任务预训练，并在部署时支持多种推理模式。

Comments https://uma-manipulation.github.io/

DDCO: Discovery of Deep Continuous Options for Robot Learning from Demonstrations

Sanjay Krishnan, Roy Fox, Ion Stoica, Ken Goldberg

专题命中 机器人学习 ：robot learning(title,journal_ref)；分类 cs.RO

Comments Published at CoRL 2017

Journal ref 1st Conference on Robot Learning (CoRL 2017)

ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow

ODEWorld：一种基于物理时间流的连续预测架构

Dongxiu Liu, Haoyi Niu, Peng Cheng, Yuan Gao, Xirui Kang, Sangli Teng, Koushil Sreenath, Xianyuan Zhan

机构 * Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR）） ； Berkeley Artificial Intelligence Research (BAIR), University of California, Berkeley（加州大学伯克利分校伯克利人工智能研究院（BAIR）） 纠错

专题命中 机器人学习 ：world model(abstract)；robotic(abstract)；分类 cs.RO、cs.CV、cs.LG

AI总结 研究针对现有世界建模机器学习范式局限于离散时间预测的问题，提出基于PT-Flow的连续时间潜在世界模型ODEWorld，解决表示崩溃问题，在视频生成和机器人控制任务中表现出色。

Imitating What Works: Simulation-Filtered Modular Policy Learning from Human Videos

模仿有效的方法：基于仿真过滤的人类视频模块化策略学习

Albert J. Zhai, Kuo-Hao Zeng, Jiasen Lu, Ali Farhadi, Shenlong Wang, Wei-Chiu Ma

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； Allen Institute for AI（Allen人工智能研究所） ； University of Washington（华盛顿大学） ； Cornell University（康奈尔大学） 纠错

专题命中 机器人学习 ：robot learning(abstract)；manipulation(abstract)；分类 cs.RO、cs.CV、cs.LG

AI总结 提出Perceive-Simulate-Imitate框架，通过仿真过滤人类视频中的抓取-轨迹对，学习任务导向的抓取与后抓取运动策略，无需机器人数据即可实现鲁棒操作。

Comments Transactions on Machine Learning Research (TMLR)