机器人 / 具身智能 - arXivDaily 专题

2110.10255 2021-10-22 cs.LG cs.RO 73%

A Simple Approach to Continual Learning by Transferring Skill Parameters

K. R. Zentner, Ryan Julian, Ujjwal Puri, Yulun Zhang, Gaurav S. Sukhatme

专题命中机器人数据与评测：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.LG

Comments Submitted to ICRA 2022

2108.05013 2021-08-21 cs.RO cs.CV 73%

Elastic Tactile Simulation Towards Tactile-Visual Perception

Yikai Wang, Wenbing Huang, Bin Fang, Fuchun Sun, Chang Li

专题命中机器人数据与评测：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.CV

Comments ACMMM 2021 (Oral). Code available at https://github.com/yikaiw/EIP. arXiv admin note: substantial text overlap with arXiv:2011.11528

2107.04852 2021-07-13 cs.RO cs.CV 73%

SynPick: A Dataset for Dynamic Bin Picking Scene Understanding

Arul Selvam Periyasamy, Max Schwarz, Sven Behnke

专题命中机器人数据与评测：robotics(abstract)；manipulation(abstract)；分类 cs.RO、cs.CV

Comments Accepted for 17th IEEE International Conference on Automation Science and Engineering (CASE), Lyon, France, August 2021

1910.11792 2021-04-27 cs.CV cs.RO 73%

JRDB: A Dataset and Benchmark of Egocentric Robot Visual Perception of Humans in Built Environments

Roberto Martín-Martín, Mihir Patel, Hamid Rezatofighi, Abhijeet Shenoi, JunYoung Gwak, Eric Frankel, Amir Sadeghian, Silvio Savarese

专题命中机器人数据与评测：robotics(abstract)；navigation(abstract)；分类 cs.RO、cs.CV

2104.00850 2021-04-09 cs.CV cs.AI 73%

Deep ensembles based on Stochastic Activation Selection for Polyp Segmentation

Alessandra Lumini, Loris Nanni, Gianluca Maguolo

专题命中机器人数据与评测：navigation(abstract)；robotic(abstract)；分类 cs.AI、cs.CV

2102.09539 2021-03-02 cs.RO cs.AI 73%

iX-BSP: Incremental Belief Space Planning

Elad I. Farhi, Vadim Indelman

专题命中机器人数据与评测：robotics(abstract)；navigation(abstract)；分类 cs.RO、cs.AI

Comments 60 pages, 22 figures

2008.06662 2020-10-23 cs.LG cs.AI stat.ML 73%

Compositional Generalization via Neural-Symbolic Stack Machines

Xinyun Chen, Chen Liang, Adams Wei Yu, Dawn Song, Denny Zhou

专题命中机器人数据与评测：manipulation(abstract)；navigation(abstract)；分类 cs.AI、cs.LG

Comments Published in NeurIPS 2020

2005.14656 2020-06-01 cs.RO cs.AI 73%

Goal-Directed Planning for Habituated Agents by Active Inference Using a Variational Recurrent Neural Network

Takazumi Matsumoto, Jun Tani

专题命中机器人数据与评测：robotics(abstract)；robotic(abstract)；分类 cs.RO、cs.AI

Comments 30 pages, 19 figures

Journal ref Entropy 2020, 22, 564

2004.10016 2020-04-22 cs.CV cs.RO 73%

Unsupervised Domain Adaptation through Inter-modal Rotation for RGB-D Object Recognition

Mohammad Reza Loghmani, Luca Robbiano, Mirco Planamente, Kiru Park, Barbara Caputo, Markus Vincze

专题命中机器人数据与评测：robotics(abstract)；robotic(abstract)；分类 cs.RO、cs.CV

1907.03799 2020-04-22 cs.LG cs.CV cs.NE stat.ML 73%

Rehearsal-Free Continual Learning over Small Non-I.I.D. Batches

Vincenzo Lomonaco, Davide Maltoni, Lorenzo Pellegrini

专题命中机器人数据与评测：embodied agent(abstract)；robotic(abstract)；分类 cs.CV、cs.LG

Comments Accepted in the CLVision Workshop at CVPR2020: 12 pages, 7 figures, 5 tables, 3 algorithms

2003.00784 2020-03-04 cs.RO cs.LG 73%

Gaining a Sense of Touch. Physical Parameters Estimation using a Soft Gripper and Neural Networks

Michał Bednarek, Piotr Kicki, Jakub Bednarek, Krzysztof Walas

专题命中机器人数据与评测：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.LG

Comments Submitted to IEEE IROS 2020

1909.07721 2020-02-10 cs.CV cs.RO eess.IV eess.SP 73%

DS-PASS: Detail-Sensitive Panoramic Annular Semantic Segmentation through SwaftNet for Surrounding Sensing

Kailun Yang, Xinxin Hu, Hao Chen, Kaite Xiang, Kaiwei Wang, Rainer Stiefelhagen

专题命中机器人数据与评测：robotics(abstract)；navigation(abstract)；分类 cs.RO、cs.CV

Comments 8 pages, 10 figures

2002.02012 2020-02-07 cs.AI cs.LG 73%

From Route Instructions to Landmark Graphs

Christopher M Cervantes

专题命中机器人数据与评测：navigation(abstract)；robotic(abstract)；分类 cs.AI、cs.LG

2001.00605 2020-01-06 cs.LG cs.RO cs.SY eess.SY 73%

Zero-Shot Reinforcement Learning with Deep Attention Convolutional Neural Networks

Sahika Genc, Sunil Mallya, Sravan Bodapati, Tao Sun, Yunzhe Tao

专题命中机器人数据与评测：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.LG

1910.09471 2019-10-22 cs.RO cs.LG 73%

Modelling Generalized Forces with Reinforcement Learning for Sim-to-Real Transfer

Rae Jeong, Jackie Kay, Francesco Romano, Thomas Lampe, Tom Rothorl, Abbas Abdolmaleki, Tom Erez, Yuval Tassa, Francesco Nori

专题命中机器人数据与评测：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.LG

1908.05540 2019-08-16 cs.CV cs.LG 73%

To complete or to estimate, that is the question: A Multi-Task Approach to Depth Completion and Monocular Depth Estimation

Amir Atapour-Abarghouei, Toby P. Breckon

专题命中机器人数据与评测：navigation(abstract)；robotic(abstract)；分类 cs.CV、cs.LG

Comments International Conference on 3D Vision (3DV) 2019

1904.11761 2019-04-29 cs.LG cs.AI stat.ML 73%

Factored Contextual Policy Search with Bayesian Optimization

Robert Pinsler, Peter Karkus, Andras Kupcsik, David Hsu, Wee Sun Lee

专题命中机器人数据与评测：robot learning(abstract)；robotic(abstract)；分类 cs.AI、cs.LG

Comments To appear in ICRA 2019

1810.05726 2019-02-15 cs.CV cs.LG stat.ML 73%

DeepWeeds: A Multiclass Weed Species Image Dataset for Deep Learning

Alex Olsen, Dmitry A. Konovalov, Bronson Philippa, Peter Ridd, Jake C. Wood, Jamie Johns, Wesley Banks, Benjamin Girgenti, Owen Kenny, James Whinney, Brendan Calvert, Mostafa Rahimi Azghadi, Ronald D. White

专题命中机器人数据与评测：robotics(abstract)；robotic(abstract)；分类 cs.CV、cs.LG

Comments 14 pages, 8 figures, 4 tables

Journal ref Sci.Rep. 9, 2058 (2019)

1703.01661 2018-03-13 cs.RO cs.CV 73%

SegICP: Integrated Deep Semantic Segmentation and Pose Estimation

Jay M. Wong, Vincent Kee, Tiffany Le, Syler Wagner, Gian-Luca Mariottini, Abraham Schneider, Lei Hamilton, Rahul Chipalkatty, Mitchell Hebert, David M. S. Johnson, Jimmy Wu, Bolei Zhou, Antonio Torralba

专题命中机器人数据与评测：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.CV

Comments IROS camera-ready

1709.07665 2017-09-25 cs.RO cs.CV 73%

Semantic Segmentation from Limited Training Data

A. Milan, T. Pham, K. Vijay, D. Morrison, A. W. Tow, L. Liu, J. Erskine, R. Grinover, A. Gurman, T. Hunn, N. Kelly-Boxall, D. Lee, M. McTaggart, G. Rallos, A. Razjigaev, T. Rowntree, T. Shen, R. Smith, S. Wade-McCue, Z. Zhuang, C. Lehnert, G. Lin, I. Reid, P. Corke, J. Leitner

专题命中机器人数据与评测：robotics(abstract)；robotic(abstract)；分类 cs.RO、cs.CV

1709.03456 2017-09-22 cs.CV cs.AI 73%

CLAD: A Complex and Long Activities Dataset with Rich Crowdsourced Annotations

Jawad Tayyub, Majd Hawasly, David C. Hogg, Anthony G. Cohn

专题命中机器人数据与评测：robotics(abstract)；robotic(abstract)；分类 cs.AI、cs.CV

1703.03347 2017-08-04 cs.RO cs.CV 73%

A Self-supervised Learning System for Object Detection using Physics Simulation and Multi-view Pose Estimation

Chaitanya Mitash, Kostas E. Bekris, Abdeslam Boularias

专题命中机器人数据与评测：robotics(abstract)；robotic(abstract)；分类 cs.RO、cs.CV

Comments 7 pages, 6 figures, accepted at the IEEE International Conference on Intelligent Robots and Systems (IROS), Vancouver, Canada, 2017

2603.11426 2026-08-18 cs.RO 版本更新 72%

Grounding Robot Generalization in Training Data via Retrieval-Augmented VLMs

通过检索增强的视觉语言模型实现机器人在训练数据中的泛化

Jensen Gao, Dorsa Sadigh, Sandy Huang, Dhruv Shah

机构 * Stanford University（斯坦福大学）； Google DeepMind（谷歌DeepMind）； Princeton University（普林斯顿大学）

专题命中机器人数据与评测：robotics(abstract,comments)；manipulation(abstract)；分类 cs.RO

AI总结本文提出RADAR框架，通过检索和视觉语言模型分析，评估机器人策略在不同场景下的泛化能力，验证了其在大规模数据集中的有效性。

Comments IEEE Robotics and Automation Letters (RA-L)

2608.00464 2026-08-04 cs.RO 新提交 72%

Learning to Predict Contact Force Distributions from Vision Leveraging Object Geometry Priors

利用物体几何先验从视觉学习预测接触力分布

Ryo Hanai, Yukiyasu Domaea, Ixchel G. Ramirez-Alpizar, Abdullah Mustafa, Floris Erich, Tetsuya Ogata

专题命中机器人数据与评测：robotics(abstract,comments)；manipulation(abstract)；分类 cs.RO

AI总结本文提出融入物体几何先验的模型，从单张RGB图像预测三维接触力分布，经模拟与真实环境评估，该方法提升了力预测精度与下游任务性能，且可从模拟泛化到真实场景。

Comments Published in Advanced Robotics, 2026

2601.07052 2026-06-18 cs.RO 版本更新 72%

RSLCPP -- Deterministic Simulations Using ROS 2

RSLCPP——使用ROS 2进行确定性仿真

Simon Sagmeister, Marcel Weinmann, Phillip Pitschi, Markus Lienkamp

机构 * Technical University of Munich, Germany（慕尼黑技术大学）； School of Engineering & Design, Department of Mobility Systems Engineering, Institute of Automotive Technology（工程与设计学院，移动系统工程系，汽车技术研究所）； School of Engineering & Design, Department of Engineering Physics and Computation, Institute of Automatic Control（工程与设计学院，工程物理与计算系，自动控制研究所）

专题命中机器人数据与评测：robotics(abstract,comments)；robotic(abstract)；分类 cs.RO

AI总结针对ROS异步多进程设计导致仿真结果不可复现的问题，提出RSLCPP库，通过确定性回调执行实现跨平台可复现仿真，无需修改现有节点代码。

Comments Accepted for publication at the 'IEEE Robotics and Automation Practice'

1709.05746 2026-06-04 cs.RO cs.AI cs.CV cs.LG cs.SY eess.SY 72%

Adversarial Discriminative Sim-to-real Transfer of Visuo-motor Policies

对抗性判别仿真到现实的视觉-运动策略转移

Fangyi Zhang, Jürgen Leitner, Zongyuan Ge, Michael Milford, Peter Corke

机构 * Australian Centre for Robotic Vision (ACRV)（澳大利亚机器人视觉中心）； Queensland University of Technology (QUT)（昆士兰技术大学）； Monash University（墨尔本大学）

专题命中机器人数据与评测：robotic(abstract)；分类 cs.RO、cs.AI、cs.CV；robotics(comments)

AI总结本文提出对抗性判别仿真到现实转移方法，减少现实数据标注成本，在桌面上物体抓取任务中，通过视觉观测控制7自由度机械臂在障碍物中抓取蓝色立方体，仅需93个标注和186个未标注图像即可实现97.8%的成功率和1.8厘米的控制精度。

Comments Under review for the International Journal of Robotics Research

2604.16408 2026-04-21 cs.RO cs.HC 72%

An Edge-Host-Cloud Architecture for Robot-Agnostic, Caregiver-in-the-Loop Personalized Cognitive Exercise: Multi-Site Deployment in Dementia Care

一种面向机器人无关、陪护人员在环的个性化认知训练的边缘-主机-云架构：在痴呆症护理中的多地点部署

Wenzheng Zhao, Ruth Palan Lopez, Shu Fen Wung, Fengpei Yuan

机构 * Worcester Polytechnic Institute（沃斯特理工大学）

专题命中机器人数据与评测：robotics(abstract,comments)；robotic(abstract)；分类 cs.RO

AI总结本文提出了一种分布式机器人交互平台，通过整合护理人员知识、边缘智能和机器人代理，实现个性化认知训练支持。平台通过多模态信号融合实现情感感知，并通过边缘服务器实现低延迟、隐私保护的部署。

Comments 21 pages, 6 figures, 10 tables, submitted to IEEE Transactions on Robotics (T-RO)

2603.03627 2026-03-05 cs.RO 72%

Touch2Insert: Zero-Shot Peg Insertion by Touching Intersections of Peg and Hole

Touch2Insert: 通过触摸连接器与孔的交点实现零样本针插入

Masaru Yajima, Yuma Shin, Rei Kawakami, Asako Kanezaki, Kei Ota

机构 * Institute of Science Tokyo（东京科学研究所）； Mitsubishi Electric（三菱电机）

专题命中机器人数据与评测：robotics(abstract,comments)；robotic(abstract)；分类 cs.RO

AI总结 Touch2Insert通过触觉传感实现无需特定训练的零样本针插入，适用于多种连接器形状，实验显示其在模拟和真实机器人中均表现出高精度和高成功率。

Comments Accepted by ICRA 2026 (IEEE International Conference on Robotics and Automation)

2603.01475 2026-03-03 cs.CV 72%

WildCross: A Cross-Modal Large Scale Benchmark for Place Recognition and Metric Depth Estimation in Natural Environments

WildCross: 一种用于自然环境中地方识别和度量深度估计的跨模态大规模基准

Joshua Knights, Joseph Reid, Kaushik Roy, David Hall, Mark Cox, Peyman Moghadam

专题命中机器人数据与评测：robotics(abstract,comments)；robotic(abstract)；分类 cs.CV

AI总结 WildCross是一个用于自然环境中地方识别和度量深度估计的跨模态大规模基准，通过提供大规模数据集和实验验证，推动多模态机器人感知技术的发展。

Comments IEEE International Conference on Robotics & Automation (ICRA) 2026

2602.06038 2026-02-06 cs.RO cs.AI cs.CV cs.LG cs.MA 72%

CommCP: Efficient Multi-Agent Coordination via LLM-Based Communication with Conformal Prediction

CommCP：通过基于大语言模型的通信实现高效的多智能体协调

Xiaopan Zhang, Zejin Wang, Zhixu Li, Jianpeng Yao, Jiachen Li

机构 * Trustworthy Autonomous Systems Laboratory at the University of California, Riverside, CA, USA（加州大学河滨分校可信自主系统实验室）

专题命中机器人数据与评测：manipulation(abstract)；分类 cs.RO、cs.AI、cs.CV；robotics(comments)

AI总结 CommCP通过基于大语言模型的通信框架，提升多智能体协作任务的成功率和探索效率。

Comments IEEE International Conference on Robotics and Automation (ICRA 2026); Project Website: https://comm-cp.github.io/

1. 机器人数据与评测 8699 篇

A Simple Approach to Continual Learning by Transferring Skill Parameters

Elastic Tactile Simulation Towards Tactile-Visual Perception

SynPick: A Dataset for Dynamic Bin Picking Scene Understanding

JRDB: A Dataset and Benchmark of Egocentric Robot Visual Perception of Humans in Built Environments

Deep ensembles based on Stochastic Activation Selection for Polyp Segmentation

iX-BSP: Incremental Belief Space Planning

Compositional Generalization via Neural-Symbolic Stack Machines

Goal-Directed Planning for Habituated Agents by Active Inference Using a Variational Recurrent Neural Network

Unsupervised Domain Adaptation through Inter-modal Rotation for RGB-D Object Recognition

Rehearsal-Free Continual Learning over Small Non-I.I.D. Batches

Gaining a Sense of Touch. Physical Parameters Estimation using a Soft Gripper and Neural Networks

DS-PASS: Detail-Sensitive Panoramic Annular Semantic Segmentation through SwaftNet for Surrounding Sensing

From Route Instructions to Landmark Graphs

Zero-Shot Reinforcement Learning with Deep Attention Convolutional Neural Networks

Modelling Generalized Forces with Reinforcement Learning for Sim-to-Real Transfer

To complete or to estimate, that is the question: A Multi-Task Approach to Depth Completion and Monocular Depth Estimation

Factored Contextual Policy Search with Bayesian Optimization

DeepWeeds: A Multiclass Weed Species Image Dataset for Deep Learning

SegICP: Integrated Deep Semantic Segmentation and Pose Estimation

Semantic Segmentation from Limited Training Data

CLAD: A Complex and Long Activities Dataset with Rich Crowdsourced Annotations

A Self-supervised Learning System for Object Detection using Physics Simulation and Multi-view Pose Estimation

Grounding Robot Generalization in Training Data via Retrieval-Augmented VLMs

Learning to Predict Contact Force Distributions from Vision Leveraging Object Geometry Priors

RSLCPP -- Deterministic Simulations Using ROS 2

Adversarial Discriminative Sim-to-real Transfer of Visuo-motor Policies

An Edge-Host-Cloud Architecture for Robot-Agnostic, Caregiver-in-the-Loop Personalized Cognitive Exercise: Multi-Site Deployment in Dementia Care

Touch2Insert: Zero-Shot Peg Insertion by Touching Intersections of Peg and Hole

WildCross: A Cross-Modal Large Scale Benchmark for Place Recognition and Metric Depth Estimation in Natural Environments

CommCP: Efficient Multi-Agent Coordination via LLM-Based Communication with Conformal Prediction