机器人 / 具身智能 - arXivDaily 专题

2312.06686 2023-12-13 cs.CV cs.RO 91%

Robo360: A 3D Omnispective Multi-Material Robotic Manipulation Dataset

Litian Liang, Liuyu Bian, Caiwei Xiao, Jialin Zhang, Linghao Chen, Isabella Liu, Fanbo Xiang, Zhiao Huang, Hao Su

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；robotics(abstract)；world model(abstract)

2306.04932 2023-06-09 cs.RO 91%

Jigsaw-based Benchmarking for Learning Robotic Manipulation

Xiaobo Liu, Fang Wan, Sheng Ge, Haokun Wang, Haoran Sun, Chaoyang Song

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；robotics(abstract,comments)；robot learning(abstract)

Comments 7 pages, 7 figures, accepted to 2023 IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)

2101.04882 2021-03-09 cs.LG cs.AI cs.CV cs.RO 91%

Asymmetric self-play for automatic goal discovery in robotic manipulation

OpenAI OpenAI, Matthias Plappert, Raul Sampedro, Tao Xu, Ilge Akkaya, Vineet Kosaraju, Peter Welinder, Ruben D'Sa, Arthur Petron, Henrique P. d. O. Pinto, Alex Paino, Hyeonwoo Noh, Lilian Weng, Qiming Yuan, Casey Chu, Wojciech Zaremba

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；robotics(abstract,comments)；分类 cs.RO、cs.AI、cs.CV

Comments Videos are shown at https://robotics-self-play.github.io

2607.01938 2026-07-03 cs.RO cs.AI cs.CL cs.CV cs.LG 新提交 90%

PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation

PhysMani：基于物理原理的动态物体操作3D世界模型

Peng Yun, Shouwang Huang, Hao Li, Jinxi Li, Jianan Wang, Bo Yang

机构 * vLAR Group, The Hong Kong Polytechnic University（香港理工大学vLAR Group）； Astribot

专题命中机器人操作：manipulation(title,abstract)；world model(title,abstract)；embodied AI(abstract)；分类 cs.RO、cs.AI、cs.CV

AI总结提出PhysMani框架，结合物理原理的3D高斯世界模型与未来感知动作策略模型，通过在线优化学习无散度高斯速度场预测动态，在16个任务基准上超越基线方法。

Comments ECCV 2026. Code and data are available at: https://github.com/vLAR-group/PhysMani

2605.27491 2026-05-28 cs.RO 90%

GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-loop Video World Simulators for Robotic Manipulation

GE-Sim 2.0：迈向机器人操作综合闭环视频世界模拟器的路线图

Boxiang Qiu, Liliang Chen, Yue Liao, Nan Wang, Lintao Wang, Jiayi Luo, Wenzhi Zhao, Shengcong Chen, Di Chen, Ye Li, Chen Gao, Shuicheng Yan, Si Liu, Maoqing Yao, Guanghui Ren

机构 * AgiBot ； BUAA（北京航空航天大学）； LV-NUS Lab（国立大学理工学院实验室）； TJU（天津大学）

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；world model(abstract)；robot policy(abstract)

AI总结提出GE-Sim 2.0，一种基于动作条件视频生成的闭环视频世界模拟器，通过重新训练数千小时真实机器人数据并新增状态专家、世界裁判和加速框架三个模块，实现高保真动作跟随和轨迹覆盖，在WorldArena排行榜上以2B参数超越专用模型和通用视频生成器，并验证了基于其生成轨迹和奖励训练的策略在真实世界中的有效性。

2603.19418 2026-03-23 cs.RO cs.DC 90%

Speculative Policy Orchestration: A Latency-Resilient Framework for Cloud-Robotic Manipulation

推测性策略协调：一种低延迟的云机器人操控框架

Chanh Nguyen, Shutong Jin, Florian T. Pokorny, Erik Elmroth

机构 * Department of Computing Science, Umeå University（乌梅大学计算科学系）； School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology（皇家理工学院电气工程与计算机科学学院）

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；robotics(abstract)；world model(abstract)

AI总结本文提出SPO框架，通过预计算并流式传输未来运动学路径点，降低网络延迟对系统的影响，提升云机器人操控的实时性和安全性。

Comments 9 pages, 7 figures, conference submission

2512.08405 2025-12-10 cs.RO 90%

Learning Robot Manipulation from Audio World Models

从音频世界模型中学习机器人操作

Fan Zhang, Michael Gienger

机构 * Honda Research Institute EU（本田欧洲研究院）

专题命中机器人操作：manipulation(title,abstract)；world model(title,abstract)；robot policy(abstract)；robotic(abstract)

AI总结本文提出一种生成性潜在流匹配模型，用于通过预测未来音频状态提升机器人操作任务中的多模态推理能力。

2505.15685 2025-11-04 cs.RO 90%

From Grounding to Manipulation: Case Studies of Foundation Model Integration in Embodied Robotic Systems

Xiuchao Sui, Daiying Tian, Qi Sun, Ruirui Chen, Dongkyu Choi, Kenneth Kwok, Soujanya Poria

机构 * IHPC, Agency for Science, Technology and Research, Singapore（科技研究局智能技术中心，新加坡）； Nanyang Technological University, Singapore（南洋理工大学，新加坡）

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；robotics(abstract)；embodied agent(abstract)

Comments EMNLP 2025 camera ready

2509.01658 2025-09-03 cs.RO 90%

MoTo: A Zero-shot Plug-in Interaction-aware Navigation for General Mobile Manipulation

Zhenyu Wu, Angyuan Ma, Xiuwei Xu, Hang Yin, Yinan Liang, Ziwei Wang, Jiwen Lu, Haibin Yan

专题命中机器人操作：manipulation(title,abstract)；navigation(title,abstract)；robotics(abstract)；robotic(abstract)

Comments Accepted to CoRL 2025. Project Page: https://gary3410.github.io/MoTo/

2409.18707 2025-03-24 cs.RO 90%

Discrete Policy: Learning Disentangled Action Space for Multi-Task Robotic Manipulation

Kun Wu, Yichen Zhu, Jinming Li, Junjie Wen, Ning Liu, Zhiyuan Xu, Jian Tang

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；robotics(abstract)；robot learning(abstract)

Comments Accept to ICRA 2025

2405.20501 2024-06-03 cs.RO cs.AI cs.CV cs.HC cs.LG 90%

ShelfHelp: Empowering Humans to Perform Vision-Independent Manipulation Tasks with a Socially Assistive Robotic Cane

Shivendra Agrawal, Suresh Nayak, Ashutosh Naik, Bradley Hayes

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；navigation(abstract)；分类 cs.RO、cs.AI、cs.CV

Comments 8 pages, 14 figures and charts

Journal ref In AAMAS (pp. 1514-1523) 2023

2402.19432 2024-03-01 cs.RO 90%

Pushing the Limits of Cross-Embodiment Learning for Manipulation and Navigation

Jonathan Yang, Catherine Glossop, Arjun Bhorkar, Dhruv Shah, Quan Vuong, Chelsea Finn, Dorsa Sadigh, Sergey Levine

专题命中机器人操作：manipulation(title,abstract)；navigation(title,abstract)；robotics(abstract)；robotic(abstract)

Comments 16 pages, 9 figures

2306.10474 2023-10-16 cs.RO cs.AI cs.CV cs.LG 90%

A Universal Semantic-Geometric Representation for Robotic Manipulation

Tong Zhang, Yingdong Hu, Hanchen Cui, Hang Zhao, Yang Gao

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；robotics(abstract)；分类 cs.RO、cs.AI、cs.CV

Comments CoRL 2023. Project website: https://semantic-geometric-representation.github.io

1908.00722 2020-06-23 cs.LG cs.AI cs.CV stat.ML 90%

Learning to combine primitive skills: A step towards versatile robotic manipulation

Robin Strudel, Alexander Pashevich, Igor Kalevatykh, Ivan Laptev, Josef Sivic, Cordelia Schmid

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；robotics(abstract,journal_ref)；分类 cs.AI、cs.CV、cs.LG

Comments ICRA 2020. See the project webpage at https://www.di.ens.fr/willow/research/rlbc/

Journal ref IEEE ROBOTICS AND AUTOMATION LETTERS, JULY 2020. 4637-4643

2605.21133 2026-07-09 cs.RO 版本更新 90%

Humanoid Whole-Body Manipulation via Active Spatial Brain and Generalizable Action Cerebellum

通过主动空间大脑和可泛化动作小脑的人形全身 manipulation

Zhizhao Liang, Yi-Lin Wei, Xuhang Chen, Mu Lin, Yi-Xiang He, Zhexi Luo, Jun-Hui Liu, Kun-Yu Lin, Wei-Shi Zheng

机构 * School of Computer Science（计算机科学学院）； Engineering, Sun Yat-sen University（工程学院，中山大学）

专题命中机器人操作：manipulation(title,title_cn)；分类 cs.RO

AI总结本文提出了一种通用的人形 locomotion-manipulation 框架，通过主动空间大脑和可泛化动作小脑来解决复杂3D环境中空间理解困难和动作生成泛化困难的问题，展示了在多种任务和环境中的强性能。

Comments Project page: https://leungchaos.github.io/Humanoid-Whole-Body-Manipulation-via-Active-Spatial-Brain-and-Generalizable-Action-Cerebellum/

2602.09368 2026-05-13 cs.RO 90%

Certified Gradient-Based Contact-Rich Manipulation via Smoothing-Error Reachable Tubes

通过平滑误差可达管实现认证的基于梯度的接触密集 manipulation

Wei-Chen Li, Glen Chou

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

专题命中机器人操作：manipulation(title,title_cn)；分类 cs.RO；robotics(comments)

AI总结本文提出通过平滑动力学并量化补偿误差，实现接触密集 manipulation 的安全性和任务完成的认证，采用凸优化生成鲁棒反馈策略。

Comments Robotics: Science & Systems (RSS) 2026

2606.28128 2026-06-29 cs.CV cs.AI cs.RO 新提交 90%

PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation

PhysisForcing：面向机器人操作的物理增强世界模拟器

Peiwen Zhang, Yufan Deng, Shangkun Sun, Juncheng Ma, Duomin Wang, Jonas Du, Zilin Pan, Ye Huang, Hao Liang, Songyan Huang, Ruihua Zhang, Enze Xie, Ming-Yu Liu, Daquan Zhou

机构 * Peking University（北京大学）； NVIDIA（英伟达）

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；world model(abstract)；分类 cs.RO、cs.AI、cs.CV

AI总结针对视频生成模型在机器人操作模拟中物理不稳定的问题，提出PhysisForcing框架，通过像素级轨迹对齐和语义级关系对齐损失联合优化，显著提升物理一致性，在多个基准上改进基础模型，并提高下游策略成功率。

Comments Github: https://github.com/DAGroup-PKU/PhysisForcing Project website: https://dagroup-pku.github.io/PhysisForcing.github.io/#

2507.06219 2026-06-05 cs.RO cs.AI cs.LG 90%

Is Diversity All You Need for Scalable Robotic Manipulation?

多样性是否是可扩展机器人操作的全部需求？

Modi Shi, Li Chen, Jin Chen, Yuxiang Lu, Chiming Liu, Guanghui Ren, Ping Luo, Di Huang, Maoqing Yao, Hongyang Li

机构 * University of Science and Technology of China（中国科学技术大学）； Tsinghua University（清华大学）； University of California, Berkeley（加州大学伯克利分校）

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；robot learning(abstract)；分类 cs.RO、cs.AI、cs.LG

AI总结本文研究了数据多样性在机器人学习中的作用，发现任务多样性比单任务演示量更重要，多身体预训练数据在跨身体转移中可选，专家多样性可能对策略学习产生干扰，提出分布去偏方法提升性能。

Comments Code is available at https://github.com/OpenDriveLab/AgiBot-World

2603.14221 2026-03-17 cs.RO cs.AI cs.LG 90%

A Real-Time Neuro-Symbolic Ethical Governor for Safe Decision Control in Autonomous Robotic Manipulation

面向自主机器人操作的安全决策控制实时神经符号伦理控制器

Aueaphum Aueawatthanaphisut, Kuepon Aueawatthanaphisut

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；robotics(abstract)；分类 cs.RO、cs.AI、cs.LG

AI总结本文提出一种实时神经符号伦理控制器，通过整合伦理推理与风险评估机制，提升自主机器人操作中的安全决策能力，实验验证了其在不同人类接近度和操作风险下的有效性。

Comments 6 pages, 6 figures, 5 equations

2509.20841 2025-09-26 cs.RO cs.AI cs.LG 90%

ImaginationPolicy: Towards Generalizable, Precise and Reliable End-to-End Policy for Robotic Manipulation

Dekun Lu, Wei Gao, Kui Jia

机构 * Dekun Lu ∗ , Wei Gao ∗ and Kui Jia ∗（作者）

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；embodied agent(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments First two authors contribute equally. Project page: https://sites.google.com/view/imaginationpolicy

2507.23523 2025-08-04 cs.RO cs.CV cs.LG 90%

H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulation

Hongzhe Bi, Lingxuan Wu, Tianwei Lin, Hengkai Tan, Zhizhong Su, Hang Su, Jun Zhu

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；robotics(abstract)；分类 cs.RO、cs.CV、cs.LG

2406.14540 2025-07-30 cs.RO cs.AI cs.CV 90%

IRASim: A Fine-Grained World Model for Robot Manipulation

Fangqi Zhu, Hongtao Wu, Song Guo, Yuxiao Liu, Chilam Cheang, Tao Kong

机构 * Hong Kong University of Science and Technology（香港科技大学）； ByteDance Seed（字节跳动种子）

专题命中机器人操作：manipulation(title,abstract)；world model(title,abstract)；robotic(abstract)；分类 cs.RO、cs.AI、cs.CV

Comments Opensource, project website: https://gen-irasim.github.io

Journal ref ICCV 2025

2503.24361 2025-04-03 cs.RO cs.AI cs.LG 90%

Sim-and-Real Co-Training: A Simple Recipe for Vision-Based Robotic Manipulation

Abhiram Maddukuri, Zhenyu Jiang, Lawrence Yunliang Chen, Soroush Nasiriany, Yuqi Xie, Yu Fang, Wenqi Huang, Zu Wang, Zhenjia Xu, Nikita Chernyadev, Scott Reed, Ken Goldberg, Ajay Mandlekar, Linxi Fan, Yuke Zhu

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；robot learning(abstract)；分类 cs.RO、cs.AI、cs.LG

Comments Project website: https://co-training.github.io/

2503.06170 2025-03-13 cs.AI cs.CV cs.RO 90%

Object-Centric World Model for Language-Guided Manipulation

Youngjoon Jeong, Junha Chun, Soonwoo Cha, Taesup Kim

专题命中机器人操作：manipulation(title,abstract)；world model(title,abstract)；robotics(abstract)；分类 cs.RO、cs.AI、cs.CV

2410.22325 2024-10-31 cs.RO cs.AI cs.CV 90%

Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets

Guangqi Jiang, Yifei Sun, Tao Huang, Huanyu Li, Yongyuan Liang, Huazhe Xu

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；robot learning(abstract)；分类 cs.RO、cs.AI、cs.CV

2409.18082 2024-10-08 cs.RO cs.AI cs.CV 90%

SKT: Integrating State-Aware Keypoint Trajectories with Vision-Language Models for Robotic Garment Manipulation

Xin Li, Siyuan Huang, Qiaojun Yu, Zhengkai Jiang, Ce Hao, Yimeng Zhu, Hongsheng Li, Peng Gao, Cewu Lu

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；robotics(abstract)；分类 cs.RO、cs.AI、cs.CV

2304.06600 2023-04-14 cs.LG cs.CV cs.RO 90%

Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation

Mohit Sharma, Claudio Fantacci, Yuxiang Zhou, Skanda Koppula, Nicolas Heess, Jon Scholz, Yusuf Aytar

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；robotics(abstract)；分类 cs.RO、cs.CV、cs.LG

Comments ICLR'23, Project page see https://sites.google.com/view/robo-adapters/

2011.06698 2020-11-16 cs.RO cs.CV cs.LG 90%

Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation

Bryan Chen, Alexander Sax, Gene Lewis, Iro Armeni, Silvio Savarese, Amir Zamir, Jitendra Malik, Lerrel Pinto

专题命中机器人操作：manipulation(title,abstract)；navigation(title,abstract)；robotics(abstract)；分类 cs.RO、cs.CV、cs.LG

Comments Extended version of CoRL 2020 camera ready. Supplementary released separately

2509.06233 2025-09-09 cs.RO cs.CV 90%

O$^3$Afford: One-Shot 3D Object-to-Object Affordance Grounding for Generalizable Robotic Manipulation

Tongxuan Tian, Xuhui Kang, Yen-Ling Kuo

机构 * University of Virginia（弗吉尼亚大学）

专题命中机器人操作：manipulation(title,abstract)；robotic(title,abstract)；robotics(abstract)；分类 cs.RO、cs.CV

Comments Conference on Robot Learning (CoRL) 2025. Project website: https://o3afford.github.io/

2504.16693 2025-05-06 cs.LG cs.RO 90%

PIN-WM: Learning Physics-INformed World Models for Non-Prehensile Manipulation

Wenxuan Li, Hang Zhao, Zhiyuan Yu, Yu Du, Qin Zou, Ruizhen Hu, Kai Xu

机构 * National University of Defense Technology（国防科技大学）； Wuhan University（武汉大学）； Shenzhen University（深圳大学）； Guangdong Laboratory of Artificial Intelligence and Digital Economy（广东人工智能与数字经济实验室）

专题命中机器人操作：manipulation(title,abstract)；world model(title,abstract)；robotic(abstract)；分类 cs.RO、cs.LG

Comments Robotics: Science and Systems 2025

1. 机器人操作 21974 篇