机器人 / 具身智能 - arXivDaily 专题

1903.05697 2019-03-15 cs.RO cs.LG 62%

Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural Networks

Sanjay Thakur, Herke van Hoof, Juan Camilo Gamboa Higuera, Doina Precup, David Meger

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

Comments Copyright 20XX IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works

1811.07550 2018-11-20 cs.CL cs.AI cs.LG cs.NE 62%

Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning

Yuexin Wu, Xiujun Li, Jingjing Liu, Jianfeng Gao, Yiming Yang

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

Comments 8 pages, 9 figures, AAAI 2019

1802.04181 2018-10-30 cs.AI cs.LG stat.ML 62%

State Representation Learning for Control: An Overview

Timothée Lesort, Natalia Díaz-Rodríguez, Jean-François Goudou, David Filliat

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

1710.03875 2018-10-30 cs.LG cs.AI cs.LO 62%

Learning Task Specifications from Demonstrations

Marcell Vazquez-Chanlatte, Susmit Jha, Ashish Tiwari, Mark K. Ho, Sanjit A. Seshia

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

Comments NIPS 2018

1809.04993 2018-09-20 cs.RO cs.LG stat.ML 62%

Semiparametrical Gaussian Processes Learning of Forward Dynamical Models for Navigating in a Circular Maze

Diego Romeres, Devesh Jha, Alberto Dalla Libera, William Yerazunis, Daniel Nikovski

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

Comments 7 pages including the references, 5 figures. Changed title, improved the structure of the article and the images

1807.11174 2018-07-31 cs.AI cs.RO 62%

Active Object Perceiver: Recognition-guided Policy Learning for Object Searching on Mobile Robots

Xin Ye, Zhe Lin, Haoxiang Li, Shibin Zheng, Yezhou Yang

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

Comments 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018)

1801.06176 2018-05-24 cs.CL cs.AI cs.LG cs.NE 62%

Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning

Baolin Peng, Xiujun Li, Jianfeng Gao, Jingjing Liu, Kam-Fai Wong, Shang-Yu Su

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

Comments 11 pages, 8 figures, Accepted in ACL 2018

1804.08617 2018-04-25 cs.LG cs.AI stat.ML 62%

Distributed Distributional Deterministic Policy Gradients

Gabriel Barth-Maron, Matthew W. Hoffman, David Budden, Will Dabney, Dan Horgan, Dhruva TB, Alistair Muldal, Nicolas Heess, Timothy Lillicrap

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

1606.02485 2017-04-12 cs.RO cs.AI cs.HC 62%

Exploring Implicit Human Responses to Robot Mistakes in a Learning from Demonstration Task

Cory J. Hayes, Maryam Moosaei, Laurel D. Riek

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

Comments 7 pages, 2 figures, IEEE RO-MAN 2016, IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN 2016)

2606.15239 2026-06-16 cs.RO cs.CY cs.HC 新提交 61%

Co-Creating Buildable and Open Social Robot Study Companions with University Students

与大学生共同创造可构建且开放的社会机器人学习伙伴

Farnaz Baksh, Matevž B. Zorec, Feiazie Baksh, Karl Kruusamäe

机构 * University of Tartu（塔尔图大学）； University of Guyana Robotics Club（圭亚那大学机器人俱乐部）

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

AI总结针对开源机器人构建门槛高的问题，采用双钻石框架与大学生共同设计机器人学习伴侣v4.1，通过扭锁、卡扣等可装配/拆卸设计，将系统可用性从差提升至优（SUS 59.4→89.4），并降低感知工作负荷。

Comments Accepted for 18th International Conference on Social Robotics (ICSR + ART 2026), London, UK | 1-4 July 2026

1705.09415 2026-06-04 cs.RO cs.SY eess.SY 61%

Near-Optimal Belief Space Planning via T-LQG

通过T-LQG实现接近最优的信念空间规划

Mohammadhussein Rafieisakhaei, Suman Chakravorty, P. R. Kumar

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

AI总结本文提出T-LQG方法，用于非线性机器人系统在观测和运动不确定性下的规划问题，提供近优反馈控制策略，解决POMDP问题。

Comments 3 pages, 3 figures, In Robotics: Science and Systems (RSS) 2017 Workshop of "POMDPs in Robotics: State of The Art, Challenges, and Opportunities"

2605.26828 2026-05-27 cs.RO 61%

Learning Compositional Symbolic Task Rules from Demonstrations with Inductive Logic Programming

通过归纳逻辑编程从演示中学习组合符号任务规则

Oleh Borys, Karla Stepanova

机构 * Czech Institute of Informatics, Robotics and Cybernetics（捷克信息学、机器人学与自动控制研究所）

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

AI总结提出一种基于归纳逻辑编程的分解学习方法，从演示中学习可解释、可重用且支持强泛化的符号任务规则。

Comments In: ICRA 2026 Workshop on Semantics for Reliable Robot Autonomy: From Environment Understanding and Reasoning to Safe Interaction, Vienna, 2026 In: ICRA 2026, International Joint Workshop on Ontologies, Semantic Maps and Autonomous Robotics Standardization (J-WOSMARS 2026), Vienna, 2026

2502.03270 2025-11-17 cs.RO cs.AI cs.CV cs.LG 61%

The Temporal Trap: Entanglement in Pre-Trained Visual Representations for Visuomotor Policy Learning

Nikolaos Tsagkas, Andreas Sochopoulos, Duolikun Danier, Chris Xiaoxuan Lu, Oisin Mac Aodha

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

Comments This submission replaces our earlier work "When Pre-trained Visual Representations Fall Short: Limitations in Visuo-Motor Robot Learning." The original paper was split into two studies; this version focuses on temporal entanglement in pre-trained visual representations. The companion paper is "Attentive Feature Aggregation."

2411.18519 2024-11-28 cs.RO cs.MA 61%

A Talent-infused Policy-gradient Approach to Efficient Co-Design of Morphology and Task Allocation Behavior of Multi-Robot Systems

Prajit KrisshnaKumar, Steve Paul, Souma Chowdhury

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

Comments Presented in proceedings of the International Symposium on Distributed Autonomous Robotic Systems (DARS) 2024

2312.11194 2024-07-09 cs.RO 61%

Aligning Human Intent from Imperfect Demonstrations with Confidence-based Inverse soft-Q Learning

Xizhou Bu, Wenjuan Li, Zhengxiong Liu, Zhiqiang Ma, Panfeng Huang

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

Comments Our code see https://github.com/XizoB/CIQL

Journal ref IEEE Robotics and Automation Letters, vol. 9, no. 8, pp. 7150 - 7157, Aug. 2024

2209.09702 2023-02-23 eess.SY cs.RO cs.SY 61%

LEMURS: Learning Distributed Multi-Robot Interactions

Eduardo Sebastian, Thai Duong, Nikolay Atanasov, Eduardo Montijano, Carlos Sagues

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

Comments Accepted for publication at IEEE International Conference on Robotics and Automation 2023

2302.03901 2023-02-09 cs.RO 61%

Guided Learning from Demonstration for Robust Transferability

Fouad Sukkar, Victor Hernandez Moreno, Teresa Vidal-Calleja, Jochen Deuse

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

Comments 7 Pages, 7 Figures, accepted to the 2023 IEEE International Conference on Robotics and Automation (ICRA)

2111.12213 2022-02-22 cs.RO 61%

Ex-DoF: Expansion of Action Degree-of-Freedom with Virtual Camera Rotation for Omnidirectional Image

Kosuke Tahara, Noriaki Hirose

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

Comments 8 pages, 9 figures, 2 tables, IEEE International Conference on Robotics and Automation (ICRA2022)

2109.14152 2021-09-30 cs.RO cs.SY eess.SY 61%

Lyapunov-stable neural-network control

Hongkai Dai, Benoit Landry, Lujie Yang, Marco Pavone, Russ Tedrake

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

Comments Published at Robotics: Science and Systems (RSS) in July, 2021

2103.17098 2021-04-01 cs.RO 61%

Ergodic imitation: Learning from what to do and what not to do

Aleksandra Kalinowska, Ahalya Prabhakar, Kathleen Fitzsimons, Todd Murphey

专题命中机器人学习：robotics(abstract,journal_ref)；分类 cs.RO

Comments Kalinowska and Prabhakar contributed equally to this work

Journal ref International Conference on Robotics and Automation, 2021

2011.12569 2020-11-26 cs.RO cs.SY eess.SY 61%

Learning Certified Control using Contraction Metric

Dawei Sun, Susmit Jha, Chuchu Fan

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

Comments Accepted to Conference on Robot Learning (CoRL) 2020

1910.01765 2019-11-20 cs.CV 61%

Robust Semi-Supervised Monocular Depth Estimation with Reprojected Distances

Vitor Guizilini, Jie Li, Rares Ambrus, Sudeep Pillai, Adrien Gaidon

专题命中机器人学习：robotic(abstract)；分类 cs.CV；robot learning(comments)

Comments Conference on Robot Learning (CoRL 2019)

1911.02725 2019-11-11 cs.RO cs.HC 61%

Benchmark for Skill Learning from Demonstration: Impact of User Experience, Task Complexity, and Start Configuration on Performance

M. Asif Rana, Daphne Chen, S. Reza Ahmadzadeh, Jacob Williams, Vivian Chu, Sonia Chernova

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

Comments 8 pages, 8 figures, submitted to IEEE Robotics and Automation Letters, videos and website can be found at https://sites.google.com/view/rail-lfd

1902.05177 2019-09-04 cs.RO 61%

Multi-Objective Policy Generation for Multi-Robot Systems Using Riemannian Motion Policies

Anqi Li, Mustafa Mukadam, Magnus Egerstedt, Byron Boots

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

Comments The International Symposium on Robotics Research (ISRR), 2019

1810.12950 2019-03-19 cs.RO 61%

Learning to serve: an experimental study for a new learning from demonstrations framework

Okan Koc, Jan Peters

专题命中机器人学习：robotics(abstract,journal_ref)；分类 cs.RO

Journal ref IEEE Robotics and Automation Letters, vol. 4, no. 2, pp. 1784-1791, April 2019. URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8630019&isnumber=8581687

1410.4414 2014-10-17 cs.RO 61%

Prioritized Optimal Control

Andrea Del Prete, Francesco Romano, Lorenzo Natale, Giorgio Metta, Giulio Sandini, Francesco Nori

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

Comments Pre-print of the paper presented at Robotics and Automation (ICRA), IEEE International Conference on, Hong Kong, China, 2014

2409.05655 2025-03-05 cs.LG cs.AI cs.RO 60%

Interactive incremental learning of generalizable skills with local trajectory modulation

Markus Knauer, Alin Albu-Schäffer, Freek Stulp, João Silvério

机构 * German Aerospace Center (DLR)（德国航空航天中心）； School of Computation, Information and Technology (CIT), Technical University of Munich (TUM)（慕尼黑工业大学计算、信息与技术学院）

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

Comments Accepted at IEEE Robotics and Automation Letters (RA-L), 16 pages, 19 figures, 6 tables. See https://github.com/DLR-RM/interactive-incremental-learning for further information and video

Journal ref IEEE Robotics and Automation Letters (RA-L). Volume: 10, Issue: 4, April 2025, Pages 3398 - 3405

2608.23927 2026-08-26 cs.CV 新提交 57%

GlanceWAM: Sparse Test-Time Imagination for World-Action Models

GlanceWAM：面向世界-动作模型的稀疏测试时想象方法

Linhan Wang, Zijian An, Mingyuan Zhang, Chen Dai, Yi Xu, Can Cui, Zichong Yang, Yinlin Chen, Lifeng Zhou, Chang-Tien Lu

机构 * Virginia Tech（弗吉尼亚理工大学）； Drexel University（卓克索大学）； Northeastern University（东北大学）； Purdue University（普渡大学）

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

AI总结该研究提出GlanceWAM，通过异步解耦视频DiT的想象与控制，打破世界-动作模型的速度-成功率困境，在RoboCasa、LIBERO基准测试中表现优异，推理速度达48ms/块。

2608.22197 2026-08-25 cs.LG 新提交 57%

On the Capability Separation Between World-Model Policy Learning and Imitated World-Action Models

世界模型策略学习与模仿世界-动作模型之间的能力分离

Yang Yu

机构 * Nanjing University（南京大学）

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

AI总结该研究对比了直接行为克隆策略等三类策略，明确世界-动作模型学习与直接行为克隆的能力差异，指出观测演示无法识别动作效果，干预可实现零遗憾值。

2602.14255 2026-08-25 cs.RO 版本更新 57%

A Latency-Aware Framework for Visuomotor Policy Learning on Industrial Robots

面向工业机器人视觉-运动策略学习的延迟感知框架

Daniel Ruan, Salma Mozaffari, Sigrid Adriaenssens, Arash Adel

机构 * Princeton University（普林斯顿大学）

专题命中机器人学习：robotic(abstract)；分类 cs.RO

AI总结本文提出了一种面向工业机器人视觉-运动策略学习的延迟感知框架，通过优化执行策略以应对延迟问题，提升策略在现实环境中的可靠性和稳定性。

1. 机器人学习 876 篇

Uncertainty Aware Learning from Demonstrations in Multiple Contexts using Bayesian Neural Networks

Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning

State Representation Learning for Control: An Overview

Learning Task Specifications from Demonstrations

Semiparametrical Gaussian Processes Learning of Forward Dynamical Models for Navigating in a Circular Maze

Active Object Perceiver: Recognition-guided Policy Learning for Object Searching on Mobile Robots

Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning

Distributed Distributional Deterministic Policy Gradients

Exploring Implicit Human Responses to Robot Mistakes in a Learning from Demonstration Task

Co-Creating Buildable and Open Social Robot Study Companions with University Students

Near-Optimal Belief Space Planning via T-LQG

Learning Compositional Symbolic Task Rules from Demonstrations with Inductive Logic Programming

The Temporal Trap: Entanglement in Pre-Trained Visual Representations for Visuomotor Policy Learning

A Talent-infused Policy-gradient Approach to Efficient Co-Design of Morphology and Task Allocation Behavior of Multi-Robot Systems

Aligning Human Intent from Imperfect Demonstrations with Confidence-based Inverse soft-Q Learning

LEMURS: Learning Distributed Multi-Robot Interactions

Guided Learning from Demonstration for Robust Transferability

Ex-DoF: Expansion of Action Degree-of-Freedom with Virtual Camera Rotation for Omnidirectional Image

Lyapunov-stable neural-network control

Ergodic imitation: Learning from what to do and what not to do

Learning Certified Control using Contraction Metric

Robust Semi-Supervised Monocular Depth Estimation with Reprojected Distances

Benchmark for Skill Learning from Demonstration: Impact of User Experience, Task Complexity, and Start Configuration on Performance

Multi-Objective Policy Generation for Multi-Robot Systems Using Riemannian Motion Policies

Learning to serve: an experimental study for a new learning from demonstrations framework

Prioritized Optimal Control

Interactive incremental learning of generalizable skills with local trajectory modulation

GlanceWAM: Sparse Test-Time Imagination for World-Action Models

On the Capability Separation Between World-Model Policy Learning and Imitated World-Action Models

A Latency-Aware Framework for Visuomotor Policy Learning on Industrial Robots