机器人 / 具身智能

FACTR 2: Learning External Force Sensing for Commodity Robot Arms Improves Policy Learning

FACTR 2: 学习商用机器人手臂的外部力感知提升策略学习

Steven Oh, Jason Jingzhou Liu, Tony Tao, Philip Han, Kenneth Shaw, Satoshi Funabashi, Ruslan Salakhutdinov, Deepak Pathak

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Waseda University（早稻田大学） 纠错

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

AI总结 提出无需专用力传感器的数据驱动方法NEXT，可在1分钟内从10分钟自由运动数据中训练，实现与专用关节力矩传感器相当的估计，并结合FIRST采样策略提升策略学习性能。

Comments Website at https://jasonjzliu.com/factr2

BooST: Bridging Semantics and Motions for Efficient Skill Transfer

BooST：桥接语义与运动以实现高效的技能迁移

Jusuk Lee, Daesol Cho, Jonghun Shin, Seungyeon Yoo, Jonghae Park, Taekbeom Lee, H. Jin Kim

机构 * Seoul National University（首尔大学） ； Georgia Institute of Technology（佐治亚理工学院） 纠错

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

AI总结 BooST是桥接语义与运动的两阶段框架，通过跨模态VQ-VAE生成统一技能表示并蒸馏为轻量级策略，在仿真与真实机器人场景下实现了更优的少样本适配、跨领域技能迁移及鲁棒性。

Comments Project page: https://boost-robots.github.io/

RoSHI: A Versatile Robot-oriented Suit for Human Data In-the-Wild

RoSHI：一种面向机器人的多功能服装

Wenjing Margaret Mao, Jefferson Ng, Luyang Hu, Daniel Gehrig, Antonio Loquercio

机构 * Department of Electrical and Systems Engineering, University of Pennsylvania（宾夕法尼亚大学电气与系统工程系） 纠错

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

AI总结 RoSHI结合低成本稀疏IMU与Project Aria眼镜，实现从第一人称感知中估计完整3D姿态和身体形状，用于真实世界机器人学习。

Comments 8 pages, 4 figures. *Equal contribution by first three authors. Project webpage: https://roshi-mocap.github.io/

Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning

预训练视觉-语言-动作模型在持续学习中出人意料地表现出遗忘抵抗性

Huihan Liu, Changyeon Kim, Bo Liu, Minghuan Liu, Yuke Zhu

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校） ； Microsoft Superintelligence（微软超级智能） 纠错

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

AI总结 研究发现预训练的视觉-语言-动作模型在持续学习中表现出较强的遗忘抵抗性，简单经验回放在这些模型上效果显著，即使数据量小也能实现零遗忘。

Comments Project website: https://continual-vlas.github.io/forget-me-not/

Tool-as-Interface: Learning Robot Policies from Observing Human Tool Use

Haonan Chen, Cheng Zhu, Shuijing Liu, Yunzhu Li, Katherine Driggs-Campbell

机构 * University of Illinois, Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校） ； UT Austin（德克萨斯大学奥斯汀分校） ； Columbia University（哥伦比亚大学） 纠错

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

Comments Accepted to CoRL 2025. Project page: https://tool-as-interface.github.io. 17 pages, 14 figures

This&That: Language-Gesture Controlled Video Generation for Robot Planning

Boyang Wang, Nikhil Sridhar, Chao Feng, Mark Van der Merwe, Adam Fishman, Nima Fazeli, Jeong Joon Park

机构 * University of Michigan（密歇根大学） ； University of Washington（华盛顿大学） 纠错

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

Bootstrapped Model Predictive Control

Yuhang Wang, Hanwei Guo, Sizhe Wang, Long Qian, Xuguang Lan

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

Comments Published as a conference paper at ICLR 2025

CurricuVLM: Towards Safe Autonomous Driving via Personalized Safety-Critical Curriculum Learning with Vision-Language Models

Zihao Sheng, Zilin Huang, Yansong Qu, Yue Leng, Sruthi Bhavanam, Sikai Chen

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

Learning to Open and Traverse Doors with a Legged Manipulator

Mike Zhang, Yuntao Ma, Takahiro Miki, Marco Hutter

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

Body Transformer: Leveraging Robot Embodiment for Policy Learning

Carmelo Sferrazza, Dun-Ming Huang, Fangchen Liu, Jongmin Lee, Pieter Abbeel

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

Chain-of-Thought Predictive Control

Zhiwei Jia, Vineet Thumuluri, Fangchen Liu, Linghao Chen, Zhiao Huang, Hao Su

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

Comments ICML 2024; project page at https://sites.google.com/view/cotpc

PhyPlan: Generalizable and Rapid Physical Task Planning with Physics Informed Skill Networks for Robot Manipulators

Mudit Chopra, Abhinav Barnawal, Harshil Vagadia, Tamajit Banerjee, Shreshth Tuli, Souvik Chakraborty, Rohan Paul

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

Comments arXiv admin note: substantial text overlap with arXiv:2402.15767

Preference-Conditioned Language-Guided Abstraction

Andi Peng, Andreea Bobu, Belinda Z. Li, Theodore R. Sumers, Ilia Sucholutsky, Nishanth Kumar, Thomas L. Griffiths, Julie A. Shah

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

Comments HRI 2024

Interpreting Neural Policies with Disentangled Tree Representations

Tsun-Hsuan Wang, Wei Xiao, Tim Seyde, Ramin Hasani, Daniela Rus

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

Intrinsically Motivated Hierarchical Policy Learning in Multi-objective Markov Decision Processes

Sherif Abdelfattah, Kathryn Merrick, Jiankun Hu

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

Visual Foresight With a Local Dynamics Model

Colin Kohler, Robert Platt

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

Multiscale Sensor Fusion and Continuous Control with Neural CDEs

Sumeet Singh, Francis McCann Ramirez, Jacob Varley, Andy Zeng, Vikas Sindhwani

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

Comments Submitted to IEEE IROS 2022

An Efficient Image-to-Image Translation HourGlass-based Architecture for Object Pushing Policy Learning

Marco Ewerton, Angel Martínez-González, Jean-Marc Odobez

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

Comments 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Developmental Reinforcement Learning of Control Policy of a Quadcopter UAV with Thrust Vectoring Rotors

Aditya M. Deshpande, Rumit Kumar, Ali A. Minai, Manish Kumar

专题命中 机器人学习 ：navigation(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments 10 pages, 8 figures, Accepted in Dynamic Systems and Control Conference (https://event.asme.org/DSCC)

Learning visual servo policies via planner cloning

Ulrich Viereck, Kate Saenko, Robert Platt

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

Self-Supervised Correspondence in Visuomotor Policy Learning

Peter Florence, Lucas Manuelli, Russ Tedrake

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

Comments Video at: https://sites.google.com/view/visuomotor-correspondence

A Data-Efficient Deep Learning Approach for Deployable Multimodal Social Robots

Heriberto Cuayáhuitl

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

Factored Contextual Policy Search with Bayesian Optimization

Peter Karkus, Andras Kupcsik, David Hsu, Wee Sun Lee

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

Comments BayesOpt 2016, NeurIPS Workshop. A full paper extension is available at arXiv:1904.11761

Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks

Michelle A. Lee, Yuke Zhu, Krishnan Srinivasan, Parth Shah, Silvio Savarese, Li Fei-Fei, Animesh Garg, Jeannette Bohg

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

Comments ICRA 2019

Cooperative Queuing Policies for Effective Human-Multi-Robot Interaction

Masoume M. Raeissi, Alessandro Farinelli

专题命中 机器人学习 ：robot learning(abstract)；robotic(abstract)

Model-Based Policy Search for Automatic Tuning of Multivariate PID Controllers

基于模型的策略搜索用于多变量PID控制器的自动调优

Andreas Doerr, Duy Nguyen-Tuong, Alonso Marco, Stefan Schaal, Sebastian Trimpe

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

AI总结 本文提出基于模型的策略搜索框架，用于自动调优多变量PID控制器，通过数据驱动的方法解决复杂系统的控制器调优问题。

Comments Accepted final version to appear in 2017 IEEE International Conference on Robotics and Automation (ICRA)

Fast Lifelong Adaptive Inverse Reinforcement Learning from Demonstrations

Letian Chen, Sravan Jayanthi, Rohan Paleja, Daniel Martin, Viacheslav Zakharov, Matthew Gombolay

机构 * Georgia Institute of Technology（佐治亚理工学院） 纠错

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

Journal ref Proceedings of Conference on Robot Learning (CoRL) 2022

Human-Humanoid Robots Cross-Embodiment Behavior-Skill Transfer Using Decomposed Adversarial Learning from Demonstration

Junjia Liu, Zhuo Li, Minghao Yu, Zhipeng Dong, Sylvain Calinon, Darwin Caldwell, Fei Chen

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

Comments 9 pages, 8 figures. Accepted by IEEE Robotics and Automation Magazine

Conditional Neural Expert Processes for Learning Movement Primitives from Demonstration

Yigit Yildirim, Emre Ugur

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

Comments This work has been submitted to the IEEE RA-L for possible publication. Submitted to Robotics and Automation Letters on July 5, 2024

Active Uncertainty Reduction for Safe and Efficient Interaction Planning: A Shielding-Aware Dual Control Approach

Haimin Hu, David Isele, Sangjae Bae, Jaime F. Fisac

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

Comments The International Journal of Robotics Research. arXiv admin note: text overlap with arXiv:2202.07720