机器人 / 具身智能

Hybrid Consistency Policy: Decoupling Multi-Modal Diversity and Real-Time Efficiency in Robotic Manipulation

Qianyou Zhao, Yuliang Shen, Xuanran Zhai, Ce Hao, Duidi Wu, Jin Qi, Jie Hu, Qiaojun Yu

机构 * Shanghai Jiao Tong University（上海交通大学） ； National University of Singapore（国立新加坡大学） ； Shanghai AI Lab（上海人工智能实验室） 纠错

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

GelFusion: Enhancing Robotic Manipulation under Visual Constraints via Visuotactile Fusion

Shulong Jiang, Shiqi Zhao, Yuxuan Fan, Peng Yin

机构 * City University of Hong Kong（香港城市大学） ； The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州）） 纠错

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

CPG-Based Manipulation with Multi-Module Origami Robot Surface

Yuhao Jiang, Serge El Asmar, Ziqiao Wang, Serhat Demirtas, Jamie Paik

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

Comments This manuscript is under revision for possible publication in the IEEE Robotics and Automation Letters (RA-L). Copyright may be transferred to IEEE if the manuscript is accepted for publication, without further notice. Supplementary video: https://youtu.be/AEmWFmHhPOA. Code available: https://doi.org/10.5281/zenodo.14726303

Journal ref IEEE Robotics and Automation Letters (Volume: 10, Issue: 5, May 2025)

Magma: A Foundation Model for Multimodal AI Agents

Jianwei Yang, Reuben Tan, Qianhui Wu, Ruijie Zheng, Baolin Peng, Yongyuan Liang, Yu Gu, Mu Cai, Seonghyeon Ye, Joel Jang, Yuquan Deng, Lars Liden, Jianfeng Gao

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

Comments 29 pages, 16 figures, technical report from MSR

Scaling Diffusion Policy in Transformer to 1 Billion Parameters for Robotic Manipulation

Minjie Zhu, Yichen Zhu, Jinming Li, Junjie Wen, Zhiyuan Xu, Ning Liu, Ran Cheng, Chaomin Shen, Yaxin Peng, Feifei Feng, Jian Tang

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

Learning State Conditioned Linear Mappings for Low-Dimensional Control of Robotic Manipulators

Michael Przystupa, Kerrick Johnstonbaugh, Zichen Zhang, Laura Petrich, Masood Dehghan, Faezeh Haghverd, Martin Jagersand

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

Comments 7 Pages, 8 Figures, Presented at the 2023 IEEE International Conference on Robotics and Automation (ICRA)

Journal ref IEEE International Conference on Robotics and Automation (ICRA), 2023, pp. 857-863

Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control

Gunshi Gupta, Karmesh Yadav, Yarin Gal, Dhruv Batra, Zsolt Kira, Cong Lu, Tim G. J. Rudner

专题命中 机器人操作 ：embodied AI(abstract)；embodied agent(abstract)；manipulation(abstract)；navigation(abstract)

A Survey of Robotic Harvesting Systems and Enabling Technologies

Leonidas Droukas, Zoe Doulgeri, Nikolaos L. Tsakiridis, Dimitra Triantafyllou, Ioannis Kleitsiotis, Ioannis Mariolis, Dimitrios Giakoumis, Dimitrios Tzovaras, Dimitrios Kateris, Dionysis Bochtis

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

Comments 55 pages, 4 figures. Accepted for publication in Journal of Intelligent & Robotic Systems

Journal ref Journal of Intelligent & Robotic Systems volume 107, Article number: 21 (2023)

ModMag: A Modular Magnetic Micro-Robotic Manipulation Device

Max Sokolich, Max Sokolich, David Rivas, Markos Duey, Daniel Borsykowsky, Sambeeta Das

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

Visibility Maximization Controller for Robotic Manipulation

Kerry He, Rhys Newbury, Tin Tran, Jesse Haviland, Ben Burgess-Limerick, Dana Kulić, Peter Corke, Akansel Cosgun

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

Comments 8 pages, 6 figures, 7 tables, submitted to RA-L and IROS 2022

Elly: A Real-Time Failure Recovery and Data Collection System for Robotic Manipulation

Elena Galbally, Adrian Piedra, Cynthia Brosque, Oussama Khatib

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

Learning Pneumatic Non-Prehensile Manipulation with a Mobile Blower

Jimmy Wu, Xingyuan Sun, Andy Zeng, Shuran Song, Szymon Rusinkiewicz, Thomas Funkhouser

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

Comments Accepted to IEEE Robotics and Automation Letters (RA-L), 2022 and IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022. Project page: https://learning-dynamic-manipulation.cs.princeton.edu

Greedy Clustering-Based Algorithm for Improving Multi-point Robotic Manipulation Sequencing

Gavin Strunk

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

Combining Coarse and Fine Physics for Manipulation using Parallel-in-Time Integration

Wisdom C. Agboh, Daniel Ruprecht, Mehmet R. Dogar

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

Comments International Symposium on Robotics Research (ISRR), 2019

Journal ref In: Asfour T., Yoshida E., Park J., Christensen H., Khatib O. (eds) Robotics Research. ISRR 2019. Springer Proceedings in Advanced Robotics, vol 20. Springer, Cham

Surprisingly Robust In-Hand Manipulation: An Empirical Study

Aditya Bhatt, Adrian Sieler, Steffen Puhlmann, Oliver Brock

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

Comments Published in Robotics: Science and Systems 2021. Proceedings at http://www.roboticsproceedings.org/rss17/p089.html Spotlight talk at https://youtu.be/2vwdP4WjGoQ Complete video playlist at https://www.youtube.com/playlist?list=PLb-CNILz7vmt6Ae_yD9i15TrCw0S8bKCn

Journal ref Proceedings of Robotics: Science and Systems, 2021

Study of Signal Temporal Logic Robustness Metrics for Robotic Tasks Optimization

Akshay Dhonthi, Philipp Schillinger, Leonel Rozo, Daniele Nardi

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

Comments 3 pages, 4 figures and 2 tables. Presented in "IROS 2021 Workshop - Benchmarking of robotic grasping and manipulation: protocols, metrics and data analysis"

Learning Based Adaptive Force Control of Robotic Manipulation Based on Real-Time Object Stiffness Detection

Zhaoxing Deng, Xutian Deng, Miao Li

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

Episodic Memory Model for Learning Robotic Manipulation Tasks

Sanaz Behbahani, Siddharth Chhatpar, Said Zahrai, Vishakh Duggal, Mohak Sukhwani

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

An Image Based Visual Servo Approach with Deep Learning for Robotic Manipulation

Jingshu Liu, Yuan Li

专题命中 机器人操作 ：manipulation(title)；robotic(title)；分类 cs.CV

Comments Accepted by The 6th International Workshop on Advanced Computational Intelligence and Intelligent Informatics (IWACIII2019)

Robust Object Manipulation for Tactile-based Blind Grasping

Wenceslao Shaw-Cortez, Denny Oetomo, Chris Manzie, Peter Choong

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

Comments Note the original title of this work was: Object Manipulation using Robotic Hands with Varying Degrees of Grasp Knowledge. It has now been updated thanks to suggestions by the reviewers

Supervised Mixture-of-Experts for Surgical Grasping and Retraction

监督混合专家架构用于手术抓取与牵开

Lorenzo Mazza, Ariel Rodriguez, Rayan Younis, Martin Lelis, Ortrun Hellig, Chenpan Li, Sebastian Bodenstedt, Martin Wagner, Stefanie Speidel

机构 * Department of Translational Surgical Oncology, NCT/UCC Dresden, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD, Dresden, Germany（translational Surgical Oncology部门，NCT/UCC Dresden，医学院和Carl Gustav Carus大学医院，TUD，德累斯顿，德国） ； National Center for Tumor Diseases (NCT), NCT/UCC Dresden, a partnership between DKFZ, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD, and HZDR, Dresden, Germany（肿瘤疾病国家中心（NCT），NCT/UCC德累斯顿，DKFZ、医学院和Carl Gustav Carus大学医院、TUD以及HZDR之间的合作，德累斯顿，德国） ； Faculty of Computer Science, TUD, Dresden, Germany（计算机科学系，TUD，德累斯顿，德国） ； The Center for Tactile Internet with Human-in-the-Loop (CeTI), TUD, Dresden, Germany（带有Human-in-the-Loop的触觉互联网中心（CeTI），TUD，德累斯顿，德国） ； Department of Visceral, Thoracic and Vascular Surgery, Faculty of Medicine and University Hospital Carl Gustav Carus, TUD, Dresden, Germany（visceral、胸腔和血管外科部门，医学院和Carl Gustav Carus大学医院，TUD，德累斯顿，德国） 纠错

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

AI总结 本文提出一种监督混合专家架构，用于结构化手术任务，通过轻量动作解码器政策实现复杂操作，展示了在少样本下优于传统方法的性能。

Comments Accepted at Robotics:Science and Systems 2026

Triplet2Track: A Hierarchical System with Object-Centric Representations for Reliable Long-Horizon Manipulation

Triplet2Track：一种基于以对象为中心表征的可靠长 horizon 操作分层系统

Jianxiang Liu, Gaojing Zhang, Chuan Wen, Qipeng Liu, Yuxuan Zhao, Ning Guo, Wenzhao Lian

机构 * School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院） ； School of Engineering and Informatics, University of Sussex（萨塞克斯大学工程与信息学院） 纠错

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

AI总结 针对长 horizon 机器人操作可靠性难题，提出 Triplet-to-Track System（TTS），该闭环模仿学习系统用人类视频减少数据依赖，经实验平均成功率达74.8%，支持对象级与组合泛化。

Comments 8 pages, 6 figures. Accepted for presentation at the 2026 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2026)

ORPA: Online Residual Policy Adaptation for Robot Manipulation Control with Human Feedback

ORPA：基于人类反馈的机器人操控控制在线残差策略适配

Muhammad A. Muttaqien, Tomohiro Motoda, Ryo Hanai, Yukiyasu Domae

机构 * National Institute of AIST（日本国立AIST研究所） ； Embodied AI Research Team（具身人工智能研究团队） 纠错

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

AI总结 本研究提出ORPA框架，通过添加轻量反馈条件化模块实现机器人操控策略的在线残差适配，无需重训练即可纠正执行误差，在ALOHA平台的精度敏感操控任务上提升了成功率与扰动恢复能力。

Reflex: Enabling Fast and Predictive Vision-Language-Action Models for Reaction-Critical Manipulation

Reflex：面向反应关键型操作的快速且可预测的视觉-语言-动作模型

Yuxuan Chen, Wanruo Zhang, Xiao Li

机构 * Shanghai Jiao Tong University（上海交通大学） 纠错

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

AI总结 针对现有VLA模型忽略动态交互场景的问题，提出面向反应关键型操作的ReflexBench基准与无需大规模机器人数据预训练的ReflexVLA模型，其可提升动态操作性能并保持静态操作精度。

Comments 8 pages, 6 pages

SAFE-CHEM: Uncertainty-Aware Policy Switching for Robust Robotic Chemistry

SAFE-CHEM：面向稳健机器人化学的不确定性感知策略切换

Laura Jones, Shazil Shahzad, Ayesha Sana, Gabriella Pizzuto

机构 * School of Computer Science & Informatics, University of Liverpool（利物浦大学计算机科学与信息学院） ； Department of Chemistry, University of Liverpool（利物浦大学化学系） 纠错

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

AI总结 本研究针对机器人化学实验的安全风险，提出SAFE-CHEM不确定性感知框架，通过混合控制架构在不确定性超阈值时切换至备份控制器，提升任务成功率并减少安全违规，实现零样本仿真到真实的迁移。

LUCID: Latent-Skill Unified Control via Imagined Dynamics for Long-Horizon Humanoid Loco-Manipulation

LUCID：基于想象动力学的潜在技能统一控制用于长程人形机器人移动操作

Cheng Guo, Mingzhe Ni, Angelo Cangelosi, Arash Ajoudani

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

AI总结 该研究针对人形机器人长程移动操作的复杂序列任务，提出分层基于模型的强化学习框架LUCID，经模拟多物体重排实验验证，其任务成功率优于现有基线方法。

DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching

DFM-VLA：通过离散流匹配实现机器人操作的迭代动作细化

Jiayi Chen, Wenxuan Song, Jiaxin Fang, Ruiqing Yin, Jingbo Wang, Shuai Chen, Jieyuan Pei, Yikai Qin, Feifan Chen, Haodong Yan, Zhide Zhong, Wen Chen, Yan Wang, Yuxiang Gao, Haoang Li

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； Harbin Institute of Technology（哈尔滨工业大学） ； ShanghaiTech University（上海科技大学） ； Shanghai Institute of Technical Physics, CAS（中国科学院上海技术物理研究所） 纠错

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

AI总结 DFM-VLA通过离散流匹配实现机器人操作中动作token的迭代细化，采用动态概率速度场和双阶段解码策略，提升了动作生成的准确性和效率。

A Hierarchical Approach to Imitation Learning for Manipulation Tasks Requiring Time Varying Forces

针对需要时变力的操作任务的模仿学习的分层方法

Rishabh Shukla, Adithya Santhosh, Shaili Gandhi, Samrudh Moode, Satyandra K. Gupta

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

AI总结 该研究针对接触密集拆卸任务中扩散策略的延迟问题，提出DPA-FTG分层方法，解耦高低频控制，在双手电池拆卸任务上性能优于RDP等基线。

ModPack: An Extensible Teleoperation Interface for Bimanual Mobile Manipulation

ModPack：一种用于双边移动操作的可扩展遥操作接口

Joshua Citron, Renee Zbizika, Zeyi Liu, Shuran Song

机构 * Stanford University（斯坦福大学） 纠错

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

AI总结 针对现有遥操作系统扩展性和适应性不足的问题，提出ModPack可扩展遥操作系统，以统一框架支持多样机器人形式和任务，通过背包集成多种功能，经实验验证其灵活性和可复用性，并开源软硬件设计。

TransDex: Pre-training Visuo-Tactile Policy with Point Cloud Reconstruction for Dexterous Manipulation of Transparent Objects

TransDex：基于点云重建的视觉-触觉政策预训练用于透明物体的精细操作

Fengguan Li, Yifan Ma, Chen Qian, Wentao Rao, Weiwei Shang

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

AI总结 TransDex通过点云重建预训练实现视觉-触觉融合政策，解决透明物体操作中的自遮挡和深度噪声问题，提升真实机器人系统中精细操作性能。

Comments Project page: https://transdex.github.io/