机器人 / 具身智能 - arXivDaily 专题

2206.06289 2022-06-14 cs.CV cs.LG cs.MM cs.RO 85%

Silver-Bullet-3D at ManiSkill 2021: Learning-from-Demonstrations and Heuristic Rule-based Methods for Object Manipulation

Yingwei Pan, Yehao Li, Yiheng Zhang, Qi Cai, Fuchen Long, Zhaofan Qiu, Ting Yao, Tao Mei

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

Comments Accepted by ICLR 2022 Workshop on Generalizable Policy Learning in Physical World. Top-performing systems for both no interaction and no restriction tracks in SAPIEN ManiSkill Challenge 2021. The source code and model are publicly available at: https://github.com/caiqi/Silver-Bullet-3D/

2205.06714 2022-05-16 cs.RO cs.AI cs.LG 85%

Learning Keypoints from Synthetic Data for Robotic Cloth Folding

Thomas Lips, Victor-Louis De Gusseme, Francis wyffels

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

Comments Published on the ICRA 2022 Workshop on Representing and Manipulating Deformable Objects

2203.08277 2022-03-17 cs.RO cs.AI cs.LG 85%

Bi-Manual Manipulation and Attachment via Sim-to-Real Reinforcement Learning

Satoshi Kataoka, Seyed Kamyar Seyed Ghasemipour, Daniel Freeman, Igor Mordatch

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

Comments Our accompanying project webpage can be found at: https://sites.google.com/view/bimanual-attachment

2203.08141 2022-03-16 cs.CV cs.LG cs.RO 85%

Object Manipulation via Visual Target Localization

Kiana Ehsani, Ali Farhadi, Aniruddha Kembhavi, Roozbeh Mottaghi

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

2112.05251 2021-12-13 cs.RO cs.AI cs.LG 85%

Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulation

Josiah Wong, Albert Tung, Andrey Kurenkov, Ajay Mandlekar, Li Fei-Fei, Silvio Savarese, Roberto Martín-Martín

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

Comments CoRL 2021

2110.08066 2021-10-18 cs.RO cs.AI cs.LG cs.SY eess.SY 85%

Dual-Arm Adversarial Robot Learning

Elie Aljalbout

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

Comments Accepted at CoRL 2021, Blue Sky Track

2106.16118 2021-07-01 cs.RO cs.CV cs.LG 85%

SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo

Thomas Kollar, Michael Laskey, Kevin Stone, Brijen Thananjeyan, Mark Tjersland

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

Comments 19 pages, 13 figures

2103.11144 2021-06-09 cs.LG cs.AI cs.RO 85%

Unsupervised Feature Learning for Manipulation with Contrastive Domain Randomization

Carmel Rabinovitz, Niko Grupen, Aviv Tamar

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

Comments Accepted to ICRA 2021, code can be found at https://github.com/carmelrabinov/cdr

2102.11051 2021-02-23 cs.RO cs.AI cs.LG 85%

Improved Learning of Robot Manipulation Tasks via Tactile Intrinsic Motivation

Nikola Vulin, Sammy Christen, Stefan Stevsic, Otmar Hilliges

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

Comments 8 pages

2012.06738 2020-12-15 cs.RO cs.AI cs.LG 85%

Learning Multi-Arm Manipulation Through Collaborative Teleoperation

Albert Tung, Josiah Wong, Ajay Mandlekar, Roberto Martín-Martín, Yuke Zhu, Li Fei-Fei, Silvio Savarese

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

Comments First two authors contributed equally

2006.04271 2020-06-09 cs.RO cs.AI cs.LG 85%

Multi-Task Reinforcement Learning based Mobile Manipulation Control for Dynamic Object Tracking and Grasping

Cong Wang, Qifeng Zhang, Qiyan Tian, Shuo Li, Xiaohui Wang, David Lane, Yvan Petillot, Ziyang Hong, Sen Wang

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

Comments 6 pages, 7 figures, submitted to IROS2020

1911.03112 2020-04-20 cs.RO cs.CV cs.LG 85%

Accurate Vision-based Manipulation through Contact Reasoning

Alina Kloss, Maria Bauza, Jiajun Wu, Joshua B. Tenenbaum, Alberto Rodriguez, Jeannette Bohg

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

Comments accepted at ICRA 2020

1910.13395 2020-03-18 cs.RO cs.CV cs.LG 85%

Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation

Kuan Fang, Yuke Zhu, Animesh Garg, Silvio Savarese, Li Fei-Fei

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

Comments CoRL 2019

1909.13874 2020-02-28 cs.RO cs.CV cs.LG 85%

Efficient Bimanual Manipulation Using Learned Task Schemas

Rohan Chitnis, Shubham Tulsiani, Saurabh Gupta, Abhinav Gupta

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

Comments ICRA 2020 final version

1911.05321 2020-02-25 cs.RO cs.AI cs.LG 85%

IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data

Ajay Mandlekar, Fabio Ramos, Byron Boots, Silvio Savarese, Li Fei-Fei, Animesh Garg, Dieter Fox

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

1912.11032 2019-12-24 cs.RO cs.AI cs.LG 85%

Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning

Richard Li, Allan Jabri, Trevor Darrell, Pulkit Agrawal

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

Comments 10 pages, 4 figures and 1 table in main article, 3 figures and 3 tables in appendix. Supplementary website and videos at https://richardrl.github.io/relational-rl/

1912.06602 2019-12-16 cs.RO cs.AI cs.CV cs.HC 85%

That and There: Judging the Intent of Pointing Actions with Robotic Arms

Malihe Alikhani, Baber Khalid, Rahul Shome, Chaitanya Mitash, Kostas Bekris, Matthew Stone

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

Comments Accepted to AAAI 2020, New York City

1909.11128 2019-11-13 cs.RO cs.CV cs.LG 85%

Accept Synthetic Objects as Real: End-to-End Training of Attentive Deep Visuomotor Policies for Manipulation in Clutter

Pooya Abolghasemi, Ladislau Bölöni

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

Comments 6 pages, 5 figures

1910.03135 2019-10-16 cs.CV cs.LG cs.RO 85%

DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System

Ankur Handa, Karl Van Wyk, Wei Yang, Jacky Liang, Yu-Wei Chao, Qian Wan, Stan Birchfield, Nathan Ratliff, Dieter Fox

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

Comments 17 pages, first version of DexPilot

1910.03398 2019-10-15 cs.RO cs.AI cs.LG 85%

Toward Synergic Learning for Autonomous Manipulation of Deformable Tissues via Surgical Robots: An Approximate Q-Learning Approach

Sahba Aghajani Pedram, Peter Walker Ferguson, Changyeob Shin, Ankur Mehta, Erik P. Dutson, Farshid Alambeigi, Jacob Rosen

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

1905.03907 2019-05-13 cs.RO cs.AI cs.CV 85%

Building 3D Object Models during Manipulation by Reconstruction-Aware Trajectory Optimization

Kanrun Huang, Tucker Hermans

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

1707.02920 2018-04-24 cs.LG cs.AI cs.RO 85%

Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstration

Rouhollah Rahmatizadeh, Pooya Abolghasemi, Ladislau Bölöni, Sergey Levine

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

1603.03833 2017-11-23 cs.RO cs.AI cs.LG 85%

From virtual demonstration to real-world manipulation using LSTM and MDN

Rouhollah Rahmatizadeh, Pooya Abolghasemi, Aman Behal, Ladislau Bölöni

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

1306.5707 2015-04-14 cs.RO cs.AI cs.LG 85%

Synthesizing Manipulation Sequences for Under-Specified Tasks using Unrolled Markov Random Fields

Jaeyong Sung, Bart Selman, Ashutosh Saxena

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

Comments To Appear in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2014 (A preliminary version of this work was presented at International Conference of Machine Learning (ICML) workshop on Prediction with Sequential Models, 2013)

2608.19968 2026-08-21 cs.RO cs.CV 新提交 84%

PVRA: A Pointwise Key-point Voting Framework for Robotic Assembly

PVRA：用于机器人装配的逐点关键点投票框架

Kulunu Samarawickrama, Roel Pieters

机构 * Tampere University（坦佩雷大学）

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

AI总结本研究针对机器人自主渐进式装配的感知需求，提出基于3D关键点的模块化学习框架PVRA，在装配位姿估计数据集上训练后，与以物体为中心的基线及增强指标对比验证了其有效性。

Comments 14 pages, 3 figures. Accepted for presentation at the European Conference on Robotics (ECoR) 2026

2504.16738 2026-07-07 cs.RO cs.AI 版本更新 84%

MOSAIC: Skill-Centric Manipulation Planning with Physics Simulation

MOSAIC：基于物理模拟的以技能为中心的操作规划

Itamar Mishani, Yorai Shaoul, Maxim Likhachev

机构 * Robotics Institute, School of Computer Science（机器人研究所、计算机科学学院）

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

AI总结研究用预定义技能规划长期操作运动的问题，核心方法是利用物理模拟估计技能执行结果，贡献是引入MOSAIC方法，通过两个互补技能家族有效发现基于物理的解决方案。

Comments Accepted for Publication at the 2026 IEEE International Conference on Robotics and Automation (ICRA). Project page: https://skill-mosaic.github.io

2605.30350 2026-05-29 cs.RO cs.LG 84%

DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation

DynaFLIP: 通过三模态动力学引导表示重新思考机器人感知

Jusuk Lee, Seungjae Lee, Jonghun Shin, Hoseong Jung, Sungha Kim, Daesol Cho, H. Jin Kim, Jia-Bin Huang, Furong Huang

机构 * Seoul National University（首尔国立大学）； University of Maryland, College Park（马里兰大学学院公园分校）； Georgia Institute of Technology（佐治亚理工学院）

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

AI总结提出DynaFLIP，一种动力学感知的多模态预训练框架，通过图像-语言-3D流三元组训练图像编码器，利用单纯形体积最小化与余弦正则化和对比目标对齐三模态，提升机器人操作中的运动理解与泛化能力。

Comments Project website: https://dynaflip-robotics.github.io

2605.25495 2026-05-26 cs.RO cs.CV 84%

RepSAM: Bridging Foundation Models to Robotic Vision via Representation-Guided Adaptation

RepSAM: 通过表示引导的适应连接基础模型与机器人视觉

Wenhui Chu

机构 * Department of Computer Science and Engineering, Texas A&M University（计算机科学与工程系，德克萨斯大学阿马尔科分校）

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

AI总结针对基础模型在非结构化机器人视觉场景中性能下降的问题，提出RepSAM框架，通过CKA引导的秩分配策略和多模态融合模块实现参数高效微调，在减少158倍可训练参数的同时达到全微调97.9%的性能。

Comments Accepted to IJCAI-ECAI 2026 (Special Track on AI and Robotics). 8 pages, 4 figures, 12 tables

2605.00307 2026-05-04 cs.RO cs.CV 84%

A Model-based Visual Contact Localization and Force Sensing System for Compliant Robotic Grippers

基于模型的视觉接触定位与力感知系统用于柔顺机械手爪

Kaiwen Zuo, Shuyuan Yang, Zonghe Chua

机构 * Department of Electrical, Computer, and Systems Engineering, Case Western Reserve University（电气、计算机与系统工程系，凯斯西储大学）

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

AI总结本文提出基于模型的视觉力感知系统，结合迭代接触定位与通用化方法，用于柔顺机械手爪的实时力估计，实验显示其在不同物体和条件下具有较高的精度和鲁棒性。

Comments 8 pages, 6 figures, IEEE Robotics and Automation Letters

2602.12684 2026-03-26 cs.RO cs.LG 84%

Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution

Xiaomi-Robotics-0：一个具有实时执行能力的开源视觉-语言-动作模型

Rui Cai, Jun Guo, Xinze He, Piaopiao Jin, Jie Li, Bingxuan Lin, Futeng Liu, Wei Liu, Fei Ma, Kun Ma, Feng Qiu, Heng Qu, Yifei Su, Qiao Sun, Dong Wang, Donghao Wang, Yunhong Wang, Rujie Wu, Diyun Xiang, Yu Yang, Hangjun Ye, Yuan Zhang, Quanyun Zhou

机构 * Xiaomi Robotics（小米机器人）

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

AI总结本文提出Xiaomi-Robotics-0，通过精心设计的训练配方和部署策略，实现了高效且流畅的实时执行。模型在大规模跨体机器人轨迹和视觉语言数据上预训练，支持广泛的动作生成能力，并在真实机器人任务中表现出色。

Comments Project page: https://xiaomi-robotics-0.github.io

1. 机器人操作 22110 篇

Silver-Bullet-3D at ManiSkill 2021: Learning-from-Demonstrations and Heuristic Rule-based Methods for Object Manipulation

Learning Keypoints from Synthetic Data for Robotic Cloth Folding

Bi-Manual Manipulation and Attachment via Sim-to-Real Reinforcement Learning

Object Manipulation via Visual Target Localization

Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulation

Dual-Arm Adversarial Robot Learning

SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo

Unsupervised Feature Learning for Manipulation with Contrastive Domain Randomization

Improved Learning of Robot Manipulation Tasks via Tactile Intrinsic Motivation

Learning Multi-Arm Manipulation Through Collaborative Teleoperation

Multi-Task Reinforcement Learning based Mobile Manipulation Control for Dynamic Object Tracking and Grasping

Accurate Vision-based Manipulation through Contact Reasoning

Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation

Efficient Bimanual Manipulation Using Learned Task Schemas

IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data

Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning

That and There: Judging the Intent of Pointing Actions with Robotic Arms

Accept Synthetic Objects as Real: End-to-End Training of Attentive Deep Visuomotor Policies for Manipulation in Clutter

DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System

Toward Synergic Learning for Autonomous Manipulation of Deformable Tissues via Surgical Robots: An Approximate Q-Learning Approach

Building 3D Object Models during Manipulation by Reconstruction-Aware Trajectory Optimization

Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstration

From virtual demonstration to real-world manipulation using LSTM and MDN

Synthesizing Manipulation Sequences for Under-Specified Tasks using Unrolled Markov Random Fields

PVRA: A Pointwise Key-point Voting Framework for Robotic Assembly

MOSAIC: Skill-Centric Manipulation Planning with Physics Simulation

DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation

RepSAM: Bridging Foundation Models to Robotic Vision via Representation-Guided Adaptation

A Model-based Visual Contact Localization and Force Sensing System for Compliant Robotic Grippers

Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Execution