机器人 / 具身智能 - arXivDaily 专题

1905.01718 2019-05-07 cs.LG cs.AI cs.RO stat.ML 67%

Curious Meta-Controller: Adaptive Alternation between Model-Based and Model-Free Control in Deep Reinforcement Learning

Muhammad Burhan Hafez, Cornelius Weber, Matthias Kerzel, Stefan Wermter

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

Comments Accepted at IJCNN 2019

1810.11181 2019-05-06 cs.AI cs.CL cs.CV cs.LG 67%

Neural Modular Control for Embodied Question Answering

Abhishek Das, Georgia Gkioxari, Stefan Lee, Devi Parikh, Dhruv Batra

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

Comments 10 pages, 3 figures, 2 tables. Published at CoRL 2018. Webpage: https://embodiedqa.org/

1904.00511 2019-04-02 cs.LG cs.AI cs.RO 67%

Risk Averse Robust Adversarial Reinforcement Learning

Xinlei Pan, Daniel Seita, Yang Gao, John Canny

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

Comments ICRA 2019

1903.11524 2019-03-28 cs.LG cs.AI cs.RO stat.ML 67%

Autoregressive Policies for Continuous Control Deep Reinforcement Learning

Dmytro Korenkevych, A. Rupam Mahmood, Gautham Vasan, James Bergstra

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

Comments Submitted to 28th International Joint Conference on Artificial Intelligence (IJCAI 2019). Video: https://youtu.be/NCpyXBNqNmw Code: https://github.com/dkorenkevych/arp

1810.08700 2019-03-04 cs.RO cs.AI cs.LG 67%

Safe Reinforcement Learning with Model Uncertainty Estimates

Björn Lütjens, Michael Everett, Jonathan P. How

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

Comments ICRA 2019; Presented at IROS 2018 Workshop on Machine Learning in Robot Motion Planning

1902.05542 2019-02-15 cs.RO cs.CV cs.LG stat.ML 67%

Unsupervised Visuomotor Control through Distributional Planning Networks

Tianhe Yu, Gleb Shevchuk, Dorsa Sadigh, Chelsea Finn

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

Comments Videos available at https://sites.google.com/view/dpn-public/

1901.03162 2019-02-04 cs.LG cs.AI cs.CV stat.ML 67%

Motion Perception in Reinforcement Learning with Dynamic Objects

Artemij Amiranashvili, Alexey Dosovitskiy, Vladlen Koltun, Thomas Brox

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

1901.00943 2019-01-07 cs.LG cs.AI cs.NE cs.RO 67%

Self-supervised Learning of Image Embedding for Continuous Control

Carlos Florensa, Jonas Degrave, Nicolas Heess, Jost Tobias Springenberg, Martin Riedmiller

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

Comments Contributed talk at Inference to Control workshop at NeurIPS2018

1807.04742 2018-12-05 cs.LG cs.CV cs.RO stat.ML 67%

Visual Reinforcement Learning with Imagined Goals

Ashvin Nair, Vitchyr Pong, Murtaza Dalal, Shikhar Bahl, Steven Lin, Sergey Levine

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

Comments 15 pages, NeurIPS 2018

1811.08955 2018-11-26 cs.RO cs.AI cs.LG 67%

Integrating Task-Motion Planning with Reinforcement Learning for Robust Decision Making in Mobile Robots

Yuqian Jiang, Fangkai Yang, Shiqi Zhang, Peter Stone

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

1810.05394 2018-10-15 cs.LG cs.CV cs.RO stat.ML 67%

Sequential Learning of Movement Prediction in Dynamic Environments using LSTM Autoencoder

Meenakshi Sarkar, Debasish Ghose

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

Comments 4 pages

1807.05924 2018-07-18 cs.RO cs.AI cs.LG 67%

Bipedal Walking Robot using Deep Deterministic Policy Gradient

Arun Kumar, Navneet Paul, S N Omkar

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

Comments Research manuscript submitted to IEEE Symposium Series on Computational Intelligence(SSCI), 2018

1805.01956 2018-05-08 cs.RO cs.AI cs.LG 67%

Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning

Michael Everett, Yu Fan Chen, Jonathan P. How

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

1803.07067 2018-03-20 cs.LG cs.AI cs.RO stat.ML 67%

Setting up a Reinforcement Learning Task with a Real-World Robot

A. Rupam Mahmood, Dmytro Korenkevych, Brent J. Komer, James Bergstra

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

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

1802.10463 2018-03-01 cs.LG cs.AI cs.RO stat.ML 67%

DiGrad: Multi-Task Reinforcement Learning with Shared Actions

Parijat Dewangan, S Phaniteja, K Madhava Krishna, Abhishek Sarkar, Balaraman Ravindran

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

1709.10089 2018-02-27 cs.LG cs.AI cs.NE cs.RO 67%

Overcoming Exploration in Reinforcement Learning with Demonstrations

Ashvin Nair, Bob McGrew, Marcin Andrychowicz, Wojciech Zaremba, Pieter Abbeel

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

Comments 8 pages, ICRA 2018

1707.01495 2018-02-26 cs.LG cs.AI cs.NE cs.RO 67%

Hindsight Experience Replay

Marcin Andrychowicz, Filip Wolski, Alex Ray, Jonas Schneider, Rachel Fong, Peter Welinder, Bob McGrew, Josh Tobin, Pieter Abbeel, Wojciech Zaremba

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

1708.02596 2017-12-05 cs.LG cs.AI cs.RO 67%

Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning

Anusha Nagabandi, Gregory Kahn, Ronald S. Fearing, Sergey Levine

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

1708.05866 2017-11-15 cs.LG cs.AI cs.CV stat.ML 67%

A Brief Survey of Deep Reinforcement Learning

Kai Arulkumaran, Marc Peter Deisenroth, Miles Brundage, Anil Anthony Bharath

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

Comments IEEE Signal Processing Magazine, Special Issue on Deep Learning for Image Understanding (arXiv extended version)

1605.02097 2016-09-21 cs.LG cs.AI cs.CV 67%

ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning

Michał Kempka, Marek Wydmuch, Grzegorz Runc, Jakub Toczek, Wojciech Jaśkowski

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

Journal ref Proceedings of IEEE Conference of Computational Intelligence in Games 2016

1604.06778 2016-05-30 cs.LG cs.AI cs.RO 67%

Benchmarking Deep Reinforcement Learning for Continuous Control

Yan Duan, Xi Chen, Rein Houthooft, John Schulman, Pieter Abbeel

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

Comments 14 pages, ICML 2016

1303.2308 2014-04-16 cs.IR 67%

Improving adaptation of ubiquitous recommander systems by using reinforcement learning and collaborative filtering

Djallel Bouneffouf

专题命中模仿学习与强化学习：navigation(abstract)；robotic(abstract)

Comments arXiv admin note: text overlap with arXiv:1301.4351

1703.01250 2026-06-04 cs.RO cs.LG cs.SY eess.SY 66%

Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization

虚拟与现实：在强化学习中权衡模拟与物理实验

Alonso Marco, Felix Berkenkamp, Philipp Hennig, Angela P. Schoellig, Andreas Krause, Stefan Schaal, Sebastian Trimpe

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

AI总结本文提出利用模拟数据优化强化学习，通过结合低成本但不准确的模拟信息与高成本但准确的物理实验，提高效率。

Comments 7 pages, 6 figures, to appear in IEEE 2017 International Conference on Robotics and Automation (ICRA)

2605.05110 2026-05-11 cs.RO cs.AI 66%

LineRides: Line-Guided Reinforcement Learning for Bicycle Robot Stunts

LineRides: 基于线引导的强化学习用于自行车机器人特技

Seungeun Rho, Shamel Fahmi, Jeonghwan Kim, Arianna Ilvonen, Sehoon Ha, Gabriel Nelson

机构 * RAI Institute（RAI研究院）； Georgia Institute of Technology（佐治亚理工学院）

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

AI总结本文提出LineRides框架，通过空间引导线和稀疏关键姿态实现自行车机器人自主学习多样特技行为，无需示范或显式时间信息。

Comments Published in IEEE Robotics and Automation Letters (RA-L), 2026

2604.07426 2026-04-10 cs.LG cs.AI 66%

GIRL: Generative Imagination Reinforcement Learning via Information-Theoretic Hallucination Control

GIRL：通过信息论幻觉控制实现生成性想象强化学习

Prakul Sunil Hiremath

机构 * Department of Computer Science and Engineering, Visvesvaraya Technological University (VTU), Belagavi, India（维斯瓦拉亚科技大学计算机科学与工程系，贝拉加维，印度）； Aliens on Earth (AoE) Autonomous Research Group, Belagavi, India（地球外星人自主研究组，贝拉加维，印度）

专题命中模仿学习与强化学习：manipulation(abstract)；分类 cs.AI、cs.LG；world model(comments)

AI总结 GIRL通过引入跨模态锚定信号和不确定性适应信任区域瓶颈，解决模型误差累积导致的轨迹漂移问题，提升长周期任务的样本效率和回报性能。

Comments 20 pages, 2 figures, 7 tables; reinforcement learning, world models

2603.13782 2026-03-17 cs.RO cs.CV 66%

Your Vision-Language-Action Model Already Has Attention Heads For Path Deviation Detection

您的视觉-语言-动作模型已具备路径偏差检测的注意力头

Jaehwan Jeong, Evelyn Zhu, Jinying Lin, Emmanuel Jaimes, Tuan-Anh Vu, Jungseock Joo, Sangpil Kim, M. Khalid Jawed

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

AI总结本文提出一种无需训练的异常检测框架，通过监控VLA模型中的三个注意力头实时检测路径偏差，并利用轻量级RL策略进行恢复，展示了其在物理机器人上的实际鲁棒性。

Comments Keywords: Vision-Language Action (VLA), Reinforcement Learning (RL), Navigation Path Recovery, Robot Operating System (ROS)

2603.02783 2026-03-04 cs.RO cs.LG cs.MA 66%

Generative adversarial imitation learning for robot swarms: Learning from human demonstrations and trained policies

生成对抗模仿学习在机器人群体中的应用：从人类示范和训练策略中学习

Mattes Kraus, Jonas Kuckling

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

AI总结本文提出基于生成对抗模仿学习的框架，从人类示范和训练策略中学习机器人群体的集体行为，并在真实机器人上验证了其有效性。

Comments Accepted for publication at the 2026 IEEE International Conference on Robotics and Automation (ICRA 2026)

2507.15444 2026-02-25 cs.RO cs.CV 66%

Low-Latency Event-Based Velocimetry for Quadrotor Control in a Narrow Pipe

窄管道中四旋翼无人机低延迟事件基速度测量控制

Leonard Bauersfeld, Davide Scaramuzza

机构 * Robotics and Perception Group, University of Zurich（苏黎世大学机器人与感知组）

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

AI总结本文提出了一种基于实时流场测量的四旋翼无人机闭环控制方法，用于在狭窄管道中实现稳定悬停，通过低延迟事件基烟雾速度测量和强化学习控制器有效对抗气动扰动。

Comments 19 pages

Journal ref in IEEE Transactions on Robotics, vol. 42, pp. 1-19, 2026

2509.09893 2026-02-12 cs.RO cs.AI 66%

Self-Augmented Robot Trajectory: Efficient Imitation Learning via Safe Self-augmentation with Demonstrator-annotated Precision

自增强机器人轨迹：通过安全自增强实现高效的模仿学习

Hanbit Oh, Masaki Murooka, Tomohiro Motoda, Ryoichi Nakajo, Yukiyasu Domae

机构 * AIST（日本产业技术综合研究所）

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

AI总结 SART通过安全自增强技术，从单次人类演示中高效学习机器人轨迹，提升数据收集效率并减少碰撞风险。

Comments 21 pages, 10 figures, Advanced Robotics accepted 2026.02.03

2511.12848 2025-11-18 cs.RO cs.LG 66%

Structured Imitation Learning of Interactive Policies through Inverse Games

Max M. Sun, Todd Murphey

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

Comments Presented at the "Workshop on Generative Modeling Meets Human-Robot Interaction" at Robotics: Science and Systems 2025. Workshop website: https://sites.google.com/view/gai-hri/

1. 模仿学习与强化学习 4113 篇

Curious Meta-Controller: Adaptive Alternation between Model-Based and Model-Free Control in Deep Reinforcement Learning

Neural Modular Control for Embodied Question Answering

Risk Averse Robust Adversarial Reinforcement Learning

Autoregressive Policies for Continuous Control Deep Reinforcement Learning

Safe Reinforcement Learning with Model Uncertainty Estimates

Unsupervised Visuomotor Control through Distributional Planning Networks

Motion Perception in Reinforcement Learning with Dynamic Objects

Self-supervised Learning of Image Embedding for Continuous Control

Visual Reinforcement Learning with Imagined Goals

Integrating Task-Motion Planning with Reinforcement Learning for Robust Decision Making in Mobile Robots

Sequential Learning of Movement Prediction in Dynamic Environments using LSTM Autoencoder

Bipedal Walking Robot using Deep Deterministic Policy Gradient

Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning

Setting up a Reinforcement Learning Task with a Real-World Robot

DiGrad: Multi-Task Reinforcement Learning with Shared Actions

Overcoming Exploration in Reinforcement Learning with Demonstrations

Hindsight Experience Replay

Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning

A Brief Survey of Deep Reinforcement Learning

ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning

Benchmarking Deep Reinforcement Learning for Continuous Control

Improving adaptation of ubiquitous recommander systems by using reinforcement learning and collaborative filtering

Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization

LineRides: Line-Guided Reinforcement Learning for Bicycle Robot Stunts

GIRL: Generative Imagination Reinforcement Learning via Information-Theoretic Hallucination Control

Your Vision-Language-Action Model Already Has Attention Heads For Path Deviation Detection

Generative adversarial imitation learning for robot swarms: Learning from human demonstrations and trained policies

Low-Latency Event-Based Velocimetry for Quadrotor Control in a Narrow Pipe

Self-Augmented Robot Trajectory: Efficient Imitation Learning via Safe Self-augmentation with Demonstrator-annotated Precision

Structured Imitation Learning of Interactive Policies through Inverse Games