机器人 / 具身智能 - arXivDaily 专题

1911.00926 2020-06-04 cs.NE cs.AI cs.LG stat.ML 73%

Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer Architecture

Daniel Tanneberg, Elmar Rueckert, Jan Peters

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

1802.08705 2020-03-24 cs.AI cs.RO 73%

PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning

Caelan Reed Garrett, Tomás Lozano-Pérez, Leslie Pack Kaelbling

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

Comments International Conference on Automated Planning and Scheduling (ICAPS) 2020

2003.05212 2020-03-12 cs.RO cs.CV cs.HC 73%

A Mobile Robot Hand-Arm Teleoperation System by Vision and IMU

Shuang Li, Jiaxi Jiang, Philipp Ruppel, Hongzhuo Liang, Xiaojian Ma, Norman Hendrich, Fuchun Sun, Jianwei Zhang

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

2002.05189 2020-02-14 cs.LG cs.AI stat.ML 73%

Intrinsic Motivation for Encouraging Synergistic Behavior

Rohan Chitnis, Shubham Tulsiani, Saurabh Gupta, Abhinav Gupta

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

Comments ICLR 2020 camera-ready

1905.05138 2020-02-11 cs.RO cs.AI 73%

Let's Push Things Forward: A Survey on Robot Pushing

Jochen Stüber, Claudio Zito, Rustam Stolkin

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

2002.02089 2020-02-07 cs.AI cs.RO 73%

Soft Hindsight Experience Replay

Qiwei He, Liansheng Zhuang, Houqiang Li

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

Comments 7 pages, 5 figures, 1 table, submitted to IJCAI2020

2001.08477 2020-01-31 cs.LG cs.RO stat.ML 73%

Semi-supervised Grasp Detection by Representation Learning in a Vector Quantized Latent Space

Mridul Mahajan, Tryambak Bhattacharjee, Arya Krishnan, Priya Shukla, G C Nandi

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

2001.07679 2020-01-22 cs.AI cs.FL cs.RO cs.SY eess.SY math.OC 73%

Stochastic Finite State Control of POMDPs with LTL Specifications

Mohamadreza Ahmadi, Rangoli Sharan, Joel W. Burdick

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

1912.12773 2020-01-01 cs.LG cs.RO stat.ML 73%

Learning Predictive Models From Observation and Interaction

Karl Schmeckpeper, Annie Xie, Oleh Rybkin, Stephen Tian, Kostas Daniilidis, Sergey Levine, Chelsea Finn

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

1911.05185 2019-11-14 cs.RO cs.CV 73%

Pose estimation and bin picking for deformable products

Benjamin Joffe, Tevon Walker. Remi Gourdon, Konrad Ahlin

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

1910.08181 2019-10-21 cs.RO cs.LG 73%

Online Learning in Planar Pushing with Combined Prediction Model

Huidong Gao, Yi Ouyang, Masayoshi Tomizuka

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

1909.08862 2019-09-20 cs.RO cs.CV 73%

Assembly of randomly placed parts realized by using only one robot arm with a general parallel-jaw gripper

Jie Zhao, Xin Jiang, Xiaoman Wang, Shengfan Wang, Yunhui Liu

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

Comments Submitted in ICRA 2020

1909.08508 2019-09-19 cs.CV cs.RO 73%

Using Synthetic Data and Deep Networks to Recognize Primitive Shapes for Object Grasping

Yunzhi Lin, Chao Tang, Fu-Jen Chu, Patricio A. Vela

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

Comments 8 pages

1907.08770 2019-09-06 cs.RO cs.CV 73%

Inferring Occluded Geometry Improves Performance when Retrieving an Object from Dense Clutter

Andrew Price, Linyi Jin, Dmitry Berenson

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

1904.01650 2019-08-02 cs.RO cs.AI cs.CL 73%

Improving Robot Success Detection using Static Object Data

Rosario Scalise, Jesse Thomason, Yonatan Bisk, Siddhartha Srinivasa

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

Comments IROS 2019 + Appendix

1907.09133 2019-07-23 cs.RO cs.LG 73%

Speeding Up Iterative Closest Point Using Stochastic Gradient Descent

Fahira Afzal Maken, Fabio Ramos, Lionel Ott

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

Comments 7 Pages, 4 Figures, Submitted to ICRA

1905.10793 2019-05-28 cs.CV cs.AI cs.GR 73%

Unsupervised Intuitive Physics from Past Experiences

Sébastien Ehrhardt, Aron Monszpart, Niloy J. Mitra, Andrea Vedaldi

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

Comments Under review

1905.09304 2019-05-24 cs.CV cs.RO 73%

PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking

Xinke Deng, Arsalan Mousavian, Yu Xiang, Fei Xia, Timothy Bretl, Dieter Fox

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

Comments Accepted to RSS 2019

1812.02576 2019-01-11 cs.AI cs.RO 73%

That's Mine! Learning Ownership Relations and Norms for Robots

Zhi-Xuan Tan, Jake Brawer, Brian Scassellati

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

Comments 9 pg., 2 fig., accepted for AAAI-2019. Video demo: https://bit.ly/2z8obET GitHub: https://github.com/OwnageBot/ownage_bot

1808.07784 2018-10-25 cs.CV cs.LG stat.ML 73%

Time-Agnostic Prediction: Predicting Predictable Video Frames

Dinesh Jayaraman, Frederik Ebert, Alexei A. Efros, Sergey Levine

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

Comments 8 pages, plus appendices

1809.06148 2018-09-18 cs.LG cs.RO 73%

Dynamics Estimation Using Recurrent Neural Network

Astha Sharma

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

1804.00062 2018-04-03 cs.RO cs.AI 73%

Visual Robot Task Planning

Chris Paxton, Yotam Barnoy, Kapil Katyal, Raman Arora, Gregory D. Hager

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

Comments 8 pages, IEEE format, currently in review

1710.06231 2017-10-18 cs.CV cs.RO 73%

3D Object Discovery and Modeling Using Single RGB-D Images Containing Multiple Object Instances

Wim Abbeloos, Esra Ataer-Cansizoglu, Sergio Caccamo, Yuichi Taguchi, Yukiyasu Domae

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

Journal ref Proceedings International Conference on 3D Vision 2017 (pp. 431-439)

1707.04796 2017-09-27 cs.CV cs.RO 73%

LabelFusion: A Pipeline for Generating Ground Truth Labels for Real RGBD Data of Cluttered Scenes

Pat Marion, Peter R. Florence, Lucas Manuelli, Russ Tedrake

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

1504.07857 2015-05-04 cs.RO cs.CV 73%

Probabilistic Depth Image Registration incorporating Nonvisual Information

Manuel Wüthrich, Peter Pastor, Ludovic Righetti, Aude Billard, Stefan Schaal

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

1311.7295 2013-12-02 cs.RO cs.CV 73%

Glasgow's Stereo Image Database of Garments

Gerardo Aragon-Camarasa, Susanne B. Oehler, Yuan Liu, Sun Li, Paul Cockshott, J. Paul Siebert

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

Comments 7 pages, 6 figure, image database

2608.25102 2026-08-27 cs.RO 新提交 72%

ROS2 Connect: A new ROS2 over WAN Solution

ROS2 Connect：一种新型广域网环境下的ROS2解决方案

Daniel Schott, Lakshminarasimhan Srinivasan, Christian Herrmann, Andreas Nüchter

机构 * Julius-Maximilians-Universität Würzburg（维尔茨堡大学）； ENSTA（法国国立高等先进技术学院）； Institut Polytechnique de Paris（巴黎综合理工学院）； Zentrum für Telematik e.V.（电信中心协会）

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

AI总结针对ROS2在广域网中因组播机制缺失导致远程操作困难的问题，提出基于WebSocket的ROS2 Connect框架，经实验验证其在延迟、稳定性等方面优于现有方案，为广域远程机器人应用提供可靠基础。

Comments Proceedings of the 8th International Workshop on Robotics Software Engineering co-located with the 2026 IEEE International Conference on Robotics and Automation (ROSE '26)

2511.03078 2026-07-07 cs.RO 版本更新 72%

3D Cal: An Open-Source Software Library for Depth Reconstruction on Vision-Based Tactile Sensors

3D Cal：用于基于视觉的触觉传感器深度重建的开源软件库

Rohan Kota, Kaival Shah, J. Edward Colgate, Gregory Reardon

机构 * McCormick School of Engineering, Center for Robotics and Biosystems, Northwestern University（麦科姆ick工程学院，机器人与生物系统中心，西北大学）

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

AI总结介绍3D Cal开源库，将低成本3D打印机变为自动探测设备，为校准基于视觉的触觉传感器生成大量标记训练数据，还提供端到端管道训练自定义卷积网络进行深度重建，给出校准准则并展示良好性能。

Comments Accepted for publication in IEEE Robotics and Automation Letters (RA-L). Project page: https://rohankotanu.github.io/3DCal/

2606.31101 2026-07-01 cs.RO 新提交 72%

Efficient Sim-to-Real Transfer of World-Action Models from Synthetic Priors

基于合成先验的世界-动作模型的高效仿真到现实迁移

Zixing Wang, Kausik Sivakumar, Jinghuan Shang, Yafei Hu, Zhaoming Xie, Ran Gong, Xiaohan Zhang, Karl Schmeckpeper

机构 * Purdue University（普渡大学）； Robotics and AI Institute（机器人与人工智能研究所）

专题命中机器人操作：manipulation(abstract)；robotic(abstract)；分类 cs.RO；embodied AI(comments)

AI总结本文研究从合成先验训练世界-动作模型并零样本部署到真实机器人操作，通过域随机化和AnyTask运动规划生成演示，首次成功实现仿真到现实的迁移。

Comments This work is accepted by CVPR'26, Embodied AI Workshop. This paper represent a part of early result of our official world-action model zero-shot sim-to-real transfer work, which will be released soon

2510.02614 2026-06-23 cs.RO 72%

UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies

UMI-on-Air：面向无躯体感知的具身化视觉-运动策略的具身感知引导

Harsh Gupta, Xiaofeng Guo, Huy Ha, Chuer Pan, Muqing Cao, Dongjae Lee, Sebastian Scherer, Shuran Song, Guanya Shi

机构 * Carnegie Mellon University（卡内基梅隆大学）； Stanford University（斯坦福大学）

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

AI总结本文提出UMI-on-Air框架，通过手握夹具收集的多样化无约束人类示范训练通用视觉-运动策略，结合高阶UMI策略与低阶具身特定控制器，在推理时实现具身感知的轨迹自适应，提升在复杂环境中的执行效率与鲁棒性。

Comments Result videos can be found at umi-on-air.github.io

Journal ref 2026 IEEE International Conference on Robotics and Automation (ICRA)

1. 机器人操作 22164 篇

Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer Architecture

PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning

A Mobile Robot Hand-Arm Teleoperation System by Vision and IMU

Intrinsic Motivation for Encouraging Synergistic Behavior

Let's Push Things Forward: A Survey on Robot Pushing

Soft Hindsight Experience Replay

Semi-supervised Grasp Detection by Representation Learning in a Vector Quantized Latent Space

Stochastic Finite State Control of POMDPs with LTL Specifications

Learning Predictive Models From Observation and Interaction

Pose estimation and bin picking for deformable products

Online Learning in Planar Pushing with Combined Prediction Model

Assembly of randomly placed parts realized by using only one robot arm with a general parallel-jaw gripper

Using Synthetic Data and Deep Networks to Recognize Primitive Shapes for Object Grasping

Inferring Occluded Geometry Improves Performance when Retrieving an Object from Dense Clutter

Improving Robot Success Detection using Static Object Data

Speeding Up Iterative Closest Point Using Stochastic Gradient Descent

Unsupervised Intuitive Physics from Past Experiences

PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking

That's Mine! Learning Ownership Relations and Norms for Robots

Time-Agnostic Prediction: Predicting Predictable Video Frames

Dynamics Estimation Using Recurrent Neural Network

Visual Robot Task Planning

3D Object Discovery and Modeling Using Single RGB-D Images Containing Multiple Object Instances

LabelFusion: A Pipeline for Generating Ground Truth Labels for Real RGBD Data of Cluttered Scenes

Probabilistic Depth Image Registration incorporating Nonvisual Information

Glasgow's Stereo Image Database of Garments

ROS2 Connect: A new ROS2 over WAN Solution

3D Cal: An Open-Source Software Library for Depth Reconstruction on Vision-Based Tactile Sensors

Efficient Sim-to-Real Transfer of World-Action Models from Synthetic Priors

UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies