机器人 / 具身智能

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

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

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

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

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

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

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

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

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

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

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/

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

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

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

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

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

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

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

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)

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） 纠错

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

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） 纠错

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

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） 纠错

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

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） 纠错

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

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） 纠错

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

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） 纠错

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

Foundational World Models Accurately Detect Bimanual Manipulator Failures

基础世界模型准确检测双臂机械臂故障

Isaac R. Ward, Michelle Ho, Houjun Liu, Aaron Feldman, Joseph Vincent, Liam Kruse, Sean Cheong, Duncan Eddy, Mykel J. Kochenderfer, Mac Schwager

机构 * Stanford University（斯坦福大学） ； Watney Robotics（Watney机器人公司） 纠错

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

AI总结 本文提出基于视觉基础模型的双臂机械臂故障检测方法，通过压缩潜在空间中的世界模型提升检测精度，相比传统方法在参数效率和故障检测率上均表现更优。

Comments 8 pages, 5 figures, accepted at the 2026 IEEE International Conference on Robotics and Automation

PRISM: Personalized Refinement of Imitation Skills for Manipulation via Human Instructions

PRISM：通过人类指令个性化模仿技能的细化

Arnau Boix-Granell, Alberto San-Miguel-Tello, Magí Dalmau-Moreno, Néstor García

机构 * Eurecat, Centre Tecnològic Catalunya, Robotics & Automation Unit（Eurecat，加泰罗尼亚技术中心，机器人与自动化单位） 纠错

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

AI总结 PRISM通过人类指令优化机器人操作中的模仿策略，提升任务执行的鲁棒性和数据效率。

Comments 10 pages, 3 figures, Accepted for publication at European Robotics Forum 2026

ROPES: Robotic Pose Estimation via Score-Based Causal Representation Learning

Pranamya Kulkarni, Puranjay Datta, Burak Varıcı, Emre Acartürk, Karthikeyan Shanmugam, Ali Tajer

机构 * Google DeepMind（谷歌DeepMind） ； Carnegie Mellon University（卡内基梅隆大学） ； Rensselaer Polytechnic Institute（伦塞拉尔理工学院） 纠错

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

Comments A preliminary version of this paper appeared at NeurIPS 2025 Workshop on Embodied World Models for Decision Making

Probabilistic Human Intent Prediction for Mobile Manipulation: An Evaluation with Human-Inspired Constraints

Cesar Alan Contreras, Manolis Chiou, Alireza Rastegarpanah, Michal Szulik, Rustam Stolkin

机构 * United Kingdom National Nuclear Laboratory Ltd.（英国国家核实验室有限公司） 纠错

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

Comments Submitted to Journal of Intelligent & Robotic Systems (Under Review)

Certifiably Safe Manipulation of Deformable Linear Objects via Joint Shape and Tension Prediction

Yiting Zhang, Shichen Li

机构 * Department of Robotics, University of Michigan（机器人学系，密歇根大学） ； Department of Mechanical Science and Engineering, University of Illinois at Urbana-Champaign（机械科学与工程系，伊利诺伊大学厄巴纳-香槟分校） 纠错

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

Comments Accepted to ICRA 2025 Workshop on Learning Meets Model-Based Methods for Contact-Rich Manipulation