机器人 / 具身智能

Uncertainty-aware Contact-safe Model-based Reinforcement Learning

Cheng-Yu Kuo, Andreas Schaarschmidt, Yunduan Cui, Tamim Asfour, Takamitsu Matsubara

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

Comments 8 pages, Accepted by Robotics and Automation Letters with ICRA 2021 option

ACDER: Augmented Curiosity-Driven Experience Replay

Boyao Li, Tao Lu, Jiayi Li, Ning Lu, Yinghao Cai, Shuo Wang

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

Journal ref 2020 IEEE International Conference on Robotics and Automation (ICRA2020)

$H_\infty$ Model-free Reinforcement Learning with Robust Stability Guarantee

Minghao Han, Yuan Tian, Lixian Zhang, Jun Wang, Wei Pan

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

Comments NeurIPS 2019 Workshop on Robot Learning: Control and Interaction in the Real World, Vancouver, Canada

On Simple Reactive Neural Networks for Behaviour-Based Reinforcement Learning

Ameya Pore, Gerardo Aragon-Camarasa

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

Comments 6 pages, 5 figures. Accepted for publication to the International Conference on Robotics and Automation (ICRA 2020)

A Robotic Auto-Focus System based on Deep Reinforcement Learning

基于深度强化学习的机器人自动对焦系统

Xiaofan Yu, Runze Yu, Jingsong Yang, Xiaohui Duan

机构 * Center of Wireless Communication and Signal Processing（无线通信与信号处理中心） 纠错

专题命中 模仿学习与强化学习 ：robotic(title)；分类 cs.CV

AI总结 本文提出一种端到端的自动对焦方法，通过深度强化学习在视觉输入中学习对焦策略，实现自动清晰成像。方法通过离散化动作空间和应用DQN，解决自动对焦问题并推广至基于视觉的控制问题。

Comments To Appear at ICARCV 2018

LLM Trainer: Automated Robotic Data Generation via Demonstration Augmentation using LLMs

LLM Trainer：利用大语言模型通过演示增强自动生成机器人数据

Abraham George, Amir Barati Farimani

机构 * Carnegie Mellon University（卡内基梅隆大学） 纠错

专题命中 模仿学习与强化学习 ：robotic(title)；分类 cs.RO

AI总结 提出LLM Trainer，一种利用大语言模型的世界知识将少量人类演示自动扩展为大规模机器人数据集的管道，通过离线标注和在线关键姿势重定向生成新轨迹，并采用汤普森采样优化标注。

Comments 9 pages, 5 figures, 4 tables. Accepted in ICRA 2026

How to Mitigate the Distribution Shift Problem in Robotics Control: A Robust and Adaptive Approach Based on Offline to Online Imitation Learning

如何缓解机器人控制中的分布偏移问题：一种基于离线到在线模仿学习的鲁棒自适应方法

Hyung-Suk Yoon, Seung-Woo Seo

机构 * Department of Electronic and Computer Engineering, Seoul National University, Seoul, South Korea（电子与计算机工程系，首尔国立大学，首尔，韩国） 纠错

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

AI总结 提出一种鲁棒离线到自适应在线模仿学习框架，通过离线阶段利用判别器扩展状态-动作覆盖和在线阶段自监督模仿学习，缓解分布偏移问题。

Comments 8 pages, 2 figures

From Robotics to Sepsis Treatment: Offline RL via Geometric Pessimism

从机器人到败血症治疗：通过几何悲观性进行离线强化学习

Sarthak Wanjari

机构 * Sarthak Wanjari（独立研究者） 纠错

专题命中 模仿学习与强化学习 ：robotics(title)；分类 cs.LG

AI总结 Geo-IQL通过几何悲观性方法在离线强化学习中提高性能，减少计算开销，并在败血症治疗中实现更高的临床一致性

Comments 10 pages, 8 figures

Align While Search: Belief-Guided Exploratory Inference for World-Grounded Embodied Agents

对齐而搜索：基于信念的探索性推理用于世界感知的具身智能体

Seohui Bae, Jeonghye Kim, Youngchul Sung, Woohyung Lim

机构 * LG AI Research（LG人工智能研究） ； KAIST（韩国科学技术院） 纠错

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

AI总结 本文提出了一种基于信念的探索性推理方法，通过后验引导和轻量级模型实现高效的世界对齐，优于现有基线方法。

Benchmarking Population-Based Reinforcement Learning across Robotic Tasks with GPU-Accelerated Simulation

Asad Ali Shahid, Yashraj Narang, Vincenzo Petrone, Enrico Ferrentino, Ankur Handa, Dieter Fox, Marco Pavone, Loris Roveda

机构 * Dalle Molle Institute for Artificial Intelligence, IDSIA USI-SUPSI（达摩克利斯人工智能研究所，IDSIA USI-SUPSI） ； NVIDIA Corporation（NVIDIA公司） ； University of Salerno（萨勒诺大学） ； Stanford University（斯坦福大学） 纠错

专题命中 模仿学习与强化学习 ：robotic(title)；分类 cs.RO

Comments Accepted for publication at 2025 IEEE 21st International Conference on Automation Science and Engineering

Journal ref 2025 IEEE 21st International Conference on Automation Science and Engineering (CASE), Los Angeles, CA, USA, 2025, pp. 1231-1238

Decentralized Real-Time Planning for Multi-UAV Cooperative Manipulation via Imitation Learning

Shantnav Agarwal, Javier Alonso-Mora, Sihao Sun

机构 * Department for Cognitive Robotics, ME, Delft University of Technology（认知机器人系，代尔夫特理工大学） 纠错

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

Comments Accepted by IEEE MRS 2025

PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning

Dongchi Huang, Jiaqi Wang, Yang Li, Chunhe Xia, Tianle Zhang, Kaige Zhang

机构 * School of Computer Science, University of Beihang, Beijing, China（北京航空航天大学计算机学院） ； School of Computer Science, Chinese University of Hong Kong, Hongkong, China（香港中文大学计算机学院） ； JD Explore Academy, Beijing, China（京东探索研究院） ； North Automatic Control Institute, Taiyuan, China（太原北自动控制研究所） 纠错

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

Comments ICML 2025

Learning Robotic Policy with Imagined Transition: Mitigating the Trade-off between Robustness and Optimality

Wei Xiao, Shangke Lyu, Zhefei Gong, Renjie Wang, Donglin Wang

机构 * Machine Intelligence Lab (MiLAB), School of Engineering, Westlake University（人工智能实验室（MiLAB）、工程学院、西湖大学） 纠错

专题命中 模仿学习与强化学习 ：robotic(title)；分类 cs.RO

Decoding RobKiNet: Insights into Efficient Training of Robotic Kinematics Informed Neural Network

Yanlong Peng, Zhigang Wang, Ziwen He, Pengxu Chang, Chuangchuang Zhou, Yu Yan, Ming Chen

机构 * School of Mechanical Engineering, Shanghai Jiao Tong University（上海交通大学机械工程学院） ； Intel Labs China（英特尔中国实验室） ； Henan Academy of Sciences（河南省科学院） ； Intel CCG FIS（英特尔中国区研究院） 纠错

专题命中 模仿学习与强化学习 ：robotic(title)；分类 cs.RO

Overcoming Knowledge Barriers: Online Imitation Learning from Visual Observation with Pretrained World Models

Xingyuan Zhang, Philip Becker-Ehmck, Patrick van der Smagt, Maximilian Karl

机构 * Volkswagen Group（大众集团） ； Technical University of Munich（慕尼黑技术大学） ； Eötvös Loránd University Budapest（布达佩斯欧多立大学） 纠错

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

Comments Accepted at TMLR

A Generative Model Enhanced Multi-Agent Reinforcement Learning Method for Electric Vehicle Charging Navigation

Tianyang Qi, Shibo Chen, Jun Zhang

专题命中 模仿学习与强化学习 ：navigation(title)；分类 cs.LG

Reset-free Reinforcement Learning with World Models

Zhao Yang, Thomas M. Moerland, Mike Preuss, Aske Plaat, Edward S. Hu

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

Force-Aware Autonomous Robotic Surgery

Alaa Eldin Abdelaal, Jiaying Fang, Tim N. Reinhart, Jacob A. Mejia, Tony Z. Zhao, Jeannette Bohg, Allison M. Okamura

专题命中 模仿学习与强化学习 ：robotic(title)；分类 cs.RO

Dynamic Throwing with Robotic Material Handling Machines

Lennart Werner, Fang Nan, Pol Eyschen, Filippo A. Spinelli, Hongyi Yang, Marco Hutter

专题命中 模仿学习与强化学习 ：robotic(title)；分类 cs.RO

Comments Accepted by IEEE IROS 2024

Maximum Solar Energy Tracking Leverage High-DoF Robotics System with Deep Reinforcement Learning

Anjie Jiang, Kangtong Mo, Satoshi Fujimoto, Michael Taylor, Sanjay Kumar, Chiotis Dimitrios, Emilia Ruiz

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

Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning

Qi Wang, Junming Yang, Yunbo Wang, Xin Jin, Wenjun Zeng, Xiaokang Yang

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

Comments Accepted by NeurIPS 2024. Project page: https://qiwang067.github.io/coworld

Autonomous Navigation and Configuration of Integrated Access Backhauling for UAV Base Station Using Reinforcement Learning

Hongyi Zhang, Jingya Li, Zhiqiang Qi, Xingqin Lin, Anders Aronsson, Jan Bosch, Helena Holmström Olsson

专题命中 模仿学习与强化学习 ：navigation(title)；分类 cs.LG

Comments This work has been submitted to the IEEE for possible publication

Autoverse: An Evolvable Game Language for Learning Robust Embodied Agents

Sam Earle, Julian Togelius

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

Comments 9 pages, 4 figures

A Deep Reinforcement Learning Framework and Methodology for Reducing the Sim-to-Real Gap in ASV Navigation

Luis F W Batista, Junghwan Ro, Antoine Richard, Pete Schroepfer, Seth Hutchinson, Cedric Pradalier

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

Comments IROS 2024, IEEE, Oct 2024, Abu Dhabi, United Arab Emirates

Variable Time Step Reinforcement Learning for Robotic Applications

Dong Wang, Giovanni Beltrame

专题命中 模仿学习与强化学习 ：robotic(title)；分类 cs.RO

Pre-trained Transformer-Enabled Strategies with Human-Guided Fine-Tuning for End-to-end Navigation of Autonomous Vehicles

Dong Hu, Chao Huang, Jingda Wu, Hongbo Gao

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

Comments 11 pages, 7 figures, references added

MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning

Zohar Rimon, Tom Jurgenson, Orr Krupnik, Gilad Adler, Aviv Tamar

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

Fuzzy Ensembles of Reinforcement Learning Policies for Robotic Systems with Varied Parameters

Abdel Gafoor Haddad, Mohammed B. Mohiuddin, Igor Boiko, Yahya Zweiri

专题命中 模仿学习与强化学习 ：robotic(title)；分类 cs.RO

Comments arXiv admin note: text overlap with arXiv:2311.05013

Leveraging Topological Maps in Deep Reinforcement Learning for Multi-Object Navigation

Simon Hakenes, Tobias Glasmachers

专题命中 模仿学习与强化学习 ：navigation(title)；分类 cs.LG

Comments Extended Abstract, Northern Lights Deep Learning Conference 2024, 3 pages, 2 figures

LiDAR-based drone navigation with reinforcement learning

Pawel Miera, Hubert Szolc, Tomasz Kryjak

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

Comments Accepted for the XXVII Automation 2023 conference