世界模型

Learning to Race in Minutes: Infoprop Dyna on the Mini Wheelbot

分钟级学习：信息传播动力学在迷你轮车上的应用

Devdutt Subhasish, Henrik Hose, Sebastian Trimpe

机构 * Institute for Data Science in Mechanical Engineering, RWTH Aachen University（机械工程数据科学研究所，亚琛工业大学） 纠错

专题命中 具身与机器人 ：model-based reinforcement learning(abstract)；分类 cs.LG、cs.RO

AI总结 本文提出利用信息传播动力学框架，使迷你轮车在11分钟内通过真实交互学习赛道竞速，无需依赖物理仿真器。

Comments Originally submitted to the German Robotics Conference, 2026

A Reliable Indoor Navigation System for Humans Using AR-based Technique

基于AR技术的可靠室内导航系统

Vijay U. Rathod, Manav S. Sharma, Shambhavi Verma, Aadi Joshi, Sachin Aage, Sujal Shahane

专题命中 具身与机器人 ：environment model(abstract)；分类 cs.CV、cs.RO

AI总结 本文提出基于AR技术的室内导航系统，利用Vuforia Area Target和A*算法提升导航精度与用户体验，适用于校园等有限空间，但需进一步优化NavMesh以适应大规模动态环境。

Comments 6 pages, 6 figures, 2 tables, Presented at 7th International Conference on Advances in Science and Technology (ICAST 2024-25)

VideoWorld 2: Learning Transferable Knowledge from Real-world Videos

VideoWorld 2: 从真实世界视频中学习可迁移的知识

Zhongwei Ren, Yunchao Wei, Xiao Yu, Guixun Luo, Yao Zhao, Bingyi Kang, Jiashi Feng, Xiaojie Jin

机构 * Beijing Jiaotong University（北京交通大学） 纠错

专题命中 具身与机器人 ：latent dynamics(abstract)；分类 cs.CV；dynamics model(abstract)

AI总结 VideoWorld 2通过动态增强的潜在动态模型从真实世界视频中学习可迁移知识，显著提升了任务成功率和长周期推理能力。

Comments Code and models are released at: https://maverickren.github.io/VideoWorld2.github.io/

Reparameterization Flow Policy Optimization

重参数化流策略优化

Hai Zhong, Zhuoran Li, Xun Wang, Longbo Huang

专题命中 具身与机器人 ：model-based reinforcement learning(abstract)；分类 cs.AI、cs.LG

AI总结 本文提出重参数化流策略优化方法，通过联合反向传播流生成过程和系统动力学，提升模型驱动强化学习的样本效率和探索能力。

Bridging the Sim-to-Real Gap with multipanda ros2: A Real-Time ROS2 Framework for Multimanual Systems

通过multipanda ros2弥合仿真到现实的差距：一种用于多手系统的真实时间ROS2框架

Jon Škerlj, Seongjin Bien, Abdeldjallil Naceri, Sami Haddadin

专题命中 具身与机器人 ：environment model(abstract)；分类 cs.AI、cs.RO

AI总结 multipanda_ros2通过实时ROS2框架和高保真仿真整合，实现了多机器人系统的高精度控制与sim2real差距的弥合。

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

Vidar: Embodied Video Diffusion Model for Generalist Manipulation

Vidar：面向通用操作的具身视频扩散模型

Yao Feng, Hengkai Tan, Xinyi Mao, Chendong Xiang, Guodong Liu, Shuhe Huang, Hang Su, Jun Zhu

专题命中 具身与机器人 ：分类 cs.AI、cs.LG、cs.CV；dynamics model(abstract)

AI总结 Vidar通过具身视频扩散模型和掩码逆动力学模型，实现了在不同机器人形态上的通用操作，仅需少量人类演示即可超越现有基线。

mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs

mimic-video: 用于超越VLAs的通用机器人控制的视频-动作模型

Jonas Pai, Liam Achenbach, Victoriano Montesinos, Benedek Forrai, Oier Mees, Elvis Nava

机构 * mimic robotics ； Microsoft Zurich（微软瑞士分公司） ； ETH Zurich（苏黎世联邦理工学院） ； ETH AI Center（苏黎世联邦理工学院人工智能中心） ； UC Berkeley（伯克利大学） 纠错

专题命中 具身与机器人 ：分类 cs.AI、cs.LG、cs.CV；dynamics model(abstract)

AI总结 mimic-video通过结合预训练的视频模型和基于流匹配的动作解码器，实现了更有效的机器人控制，提升了样本效率和收敛速度。

Comments Revised Introduction, Related Work, and Appendix. Additional minor notational and grammatical fixes

Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision

Xiaofeng Han, Shunpeng Chen, Zenghuang Fu, Zhe Feng, Lue Fan, Dong An, Changwei Wang, Li Guo, Weiliang Meng, Xiaopeng Zhang, Rongtao Xu, Shibiao Xu

机构 * aThe State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, China [1ex] bSchool of Artificial Intelligence, University of Chinese Academy of Sciences, China [1ex] cSchool of Artificial Intelligence, Beijing University of Posts ； Telecommunications, China [1ex] dKey Laboratory of Computing Power Network ； Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences), China [1ex] e Shandong Provincial Key Laboratory of Computing Power Internet ； Service Computing, Shandong Fundamental Research Center for Computer Science, China 纠错

专题命中 具身与机器人 ：environment model(abstract)；分类 cs.CV、cs.RO

Comments 27 pages, 11 figures. Accepted to Information Fusion. Final journal version: volume 126 (Part B), February 2026

Journal ref Information Fusion, 126 (Part B), February 2026, 103652

Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning

Zizhao Wang, Caroline Wang, Xuesu Xiao, Yuke Zhu, Peter Stone

专题命中 具身与机器人 ：分类 cs.AI、cs.LG、cs.RO；dynamics model(abstract)；simulation model(abstract)

Comments Accepted at AAAI24

Journal ref Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI 2024), Article 1759, Pages 15778 - 15786

Bregman Centroid Guided Cross-Entropy Method

Yuliang Gu, Hongpeng Cao, Marco Caccamo, Naira Hovakimyan

机构 * Department of Mechanical Science and Engineering, UIUC, United States（伊利诺伊大学厄巴纳-香槟分校机械科学与工程系） ； School of Engineering and Design, TUM, Germany（慕尼黑工业大学工程与设计学院） 纠错

专题命中 具身与机器人 ：model-based reinforcement learning(abstract)；分类 cs.AI、cs.LG

Transformer-based deep imitation learning for dual-arm robot manipulation

Heecheol Kim, Yoshiyuki Ohmura, Yasuo Kuniyoshi

机构 * The University of Tokyo（东京大学） 纠错

专题命中 具身与机器人 ：environment model(abstract)；分类 cs.AI、cs.RO

Comments 8 pages. Accepted in 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Review

Chengmin Zhou, Ville Kyrki, Pasi Fränti, Laura Ruotsalainen

专题命中 具身与机器人 ：model-based RL(abstract)；分类 cs.AI、cs.LG

Train Robots in a JIF: Joint Inverse and Forward Dynamics with Human and Robot Demonstrations

Gagan Khandate, Boxuan Wang, Sarah Park, Weizhe Ni, Joaquin Palacios, Kathyrn Lampo, Philippe Wu, Rosh Ho, Eric Chang, Matei Ciocarlie

机构 * Dept. of Computer Science（计算机科学系） ； Dept. of Mechanical Engineering（机械工程系） ； Columbia University（哥伦比亚大学） 纠错

专题命中 具身与机器人 ：latent dynamics(abstract)；分类 cs.RO；dynamics model(abstract)

Comments 9 pages, 8 figures, submission to RSS 2025

Next-Best-Trajectory Planning of Robot Manipulators for Effective Observation and Exploration

Heiko Renz, Maximilian Krämer, Frank Hoffmann, Torsten Bertram

专题命中 具身与机器人 ：environment model(abstract)；分类 cs.CV、cs.RO

Comments Accepted for publication at the IEEE International Conference on Robotics and Automation (ICRA), 2025

Gaussian Splatting Visual MPC for Granular Media Manipulation

Wei-Cheng Tseng, Ellina Zhang, Krishna Murthy Jatavallabhula, Florian Shkurti

专题命中 具身与机器人 ：latent dynamics(abstract)；分类 cs.RO；dynamics model(abstract)

Comments project website https://weichengtseng.github.io/gs-granular-mani/

Probabilistic Artificial Intelligence

Andreas Krause, Jonas Hübotter

专题命中 具身与机器人 ：model-based RL(abstract)；分类 cs.AI、cs.LG

Make a Donut: Hierarchical EMD-Space Planning for Zero-Shot Deformable Manipulation with Tools

Yang You, Bokui Shen, Congyue Deng, Haoran Geng, Songlin Wei, He Wang, Leonidas Guibas

专题命中 具身与机器人 ：latent dynamics(abstract)；分类 cs.AI、cs.RO

Comments 8 pages. IEEE Robotics and Automation Letters (RA-L). Preprint Version. Accepted January, 2025

DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control

Zichen Jeff Cui, Hengkai Pan, Aadhithya Iyer, Siddhant Haldar, Lerrel Pinto

专题命中 具身与机器人 ：分类 cs.AI、cs.LG、cs.CV；dynamics model(abstract)

Hierarchical Learning Framework for Whole-Body Model Predictive Control of a Real Humanoid Robot

Koji Ishihara, Hiroaki Gomi, Jun Morimoto

专题命中 具身与机器人 ：model-based reinforcement learning(abstract)；分类 cs.RO；dynamics model(abstract)

Comments 12 pages, 7 figures

Bridging the Sim-to-Real Gap with Bayesian Inference

Jonas Rothfuss, Bhavya Sukhija, Lenart Treven, Florian Dörfler, Stelian Coros, Andreas Krause

专题命中 具身与机器人 ：model-based RL(abstract)；分类 cs.LG、cs.RO

MRHER: Model-based Relay Hindsight Experience Replay for Sequential Object Manipulation Tasks with Sparse Rewards

Yuming Huang, Bin Ren, Ziming Xu, Lianghong Wu

专题命中 具身与机器人 ：model-based RL(abstract)；分类 cs.AI、cs.RO

Push Past Green: Learning to Look Behind Plant Foliage by Moving It

Xiaoyu Zhang, Saurabh Gupta

专题命中 具身与机器人 ：分类 cs.AI、cs.LG、cs.CV；dynamics model(abstract)

Comments Accepted by Conference on Robot Learning (CoRL) 2023. for project website with video, see https://sites.google.com/view/pushpastgreen/

Cross-Embodiment Robot Manipulation Skill Transfer using Latent Space Alignment

Tianyu Wang, Dwait Bhatt, Xiaolong Wang, Nikolay Atanasov

专题命中 具身与机器人 ：latent dynamics(abstract)；分类 cs.AI、cs.RO

Comments 8 pages, 9 figures

Action Conditioned Tactile Prediction: case study on slip prediction

Willow Mandil, Kiyanoush Nazari, Amir Ghalamzan E

专题命中 具身与机器人 ：分类 cs.AI、cs.LG、cs.RO；predictive model(abstract)；predictive models(abstract)

Comments Proceeding of Robotics: Science and Systems (RSS 2022)

Data-efficient, Explainable and Safe Box Manipulation: Illustrating the Advantages of Physical Priors in Model-Predictive Control

Achkan Salehi, Stephane Doncieux

专题命中 具身与机器人 ：model-based RL(abstract)；分类 cs.LG、cs.RO

Comments accepted for publication by l4dc 2024, 12 pages (with references), 4 figures, 2 tables

VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models

Wenlong Huang, Chen Wang, Ruohan Zhang, Yunzhu Li, Jiajun Wu, Li Fei-Fei

专题命中 具身与机器人 ：分类 cs.AI、cs.LG、cs.CV；dynamics model(abstract)

Translating Universal Scene Descriptions into Knowledge Graphs for Robotic Environment

Giang Hoang Nguyen, Daniel Bessler, Simon Stelter, Mihai Pomarlan, Michael Beetz

专题命中 具身与机器人 ：environment model(abstract)；分类 cs.AI、cs.RO

Comments 6 pages, 3 figures, ICRA 2024

SACSoN: Scalable Autonomous Control for Social Navigation

Noriaki Hirose, Dhruv Shah, Ajay Sridhar, Sergey Levine

专题命中 具身与机器人 ：分类 cs.LG、cs.CV、cs.RO；predictive model(abstract)；predictive models(abstract)

Comments 11 pages, 15 figures, 4 tables

SlotGNN: Unsupervised Discovery of Multi-Object Representations and Visual Dynamics

Alireza Rezazadeh, Athreyi Badithela, Karthik Desingh, Changhyun Choi

专题命中 具身与机器人 ：分类 cs.AI、cs.LG、cs.CV；dynamics model(abstract)

Practical Probabilistic Model-based Deep Reinforcement Learning by Integrating Dropout Uncertainty and Trajectory Sampling

Wenjun Huang, Yunduan Cui, Huiyun Li, Xinyu Wu

专题命中 具身与机器人 ：model-based reinforcement learning(abstract)；分类 cs.AI、cs.LG