机器人 / 具身智能

Generation of Uncertainty-Aware High-Level Spatial Concepts in Factorized 3D Scene Graphs via Graph Neural Networks

通过图神经网络生成因子化3D场景图中的不确定性感知高层空间概念

Jose Andres Millan-Romera, Muhammad Shaheer, Miguel Fernandez-Cortizas, Martin R. Oswald, Holger Voos, Jose Luis Sanchez-Lopez

机构 * Automation and Robotics Research Group, Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg（卢森堡大学自动化与机器人研究组，安全、可靠性与信任跨学科研究中心（SnT）） 纠错

专题命中 具身导航 ：navigation(abstract)；分类 cs.RO、cs.LG；robotics(comments)

AI总结 本文提出一种基于学习的方法，通过在线推断垂直平面中的空间概念，并将其作为SLAM后端可优化的因素，从而提升室内导航和映射的鲁棒性。

Comments Accepted at IEEE Robotics and Automation Letters (RA-L)

Enhanced UAV Path Planning Using the Tangent Intersection Guidance (TIG) Algorithm

利用切线交点引导算法（TIG）增强的无人机路径规划

Hichem Cheriet, Khellat Kihel Badra, Chouraqui Samira

机构 * Journal of Automation, Mobile Robotics and Intelligent Systems（自动化、移动机器人与智能系统杂志） 纠错

专题命中 具身导航 ：navigation(abstract)；分类 cs.RO、cs.CV；robotics(journal_ref)

AI总结 本文提出TIG算法，通过椭圆切线交点方法生成可行路径，结合启发式规则和二次贝塞尔曲线平滑技术，在静态和动态环境中实现高效安全的无人机路径规划。

Comments Accepted for publication in JAMRIS Journal

Journal ref Journal of Automation, Mobile Robotics and Intelligent Systems, 20(2), 30-52 (2026)

Magnetic Indoor Localization through CNN Regression and Rotation Invariance

基于CNN回归和旋转不变性的磁室内定位

Helge Rosé, Konstantin Klipp, Tom Koubek, Bernd Schäufele, Ilja Radusch

机构 * University of Freiburg（弗赖堡大学） 纠错

专题命中 具身导航 ：navigation(abstract)；分类 cs.RO、cs.LG；robotics(comments)

AI总结 提出使用旋转不变特征（磁场强度和重力轴投影）训练轻量级CNN模型，实现无需方向校准的室内定位，在MagPie数据集上达到或超越现有最优精度。

Comments Published and presented at the 2026 4th International Conference on Mechatronics, Control and Robotics (ICMCR)

Safe Bayesian Optimization for Complex Control Systems via Additive Gaussian Processes

通过加性高斯过程实现复杂控制系统安全贝叶斯优化

Hongxuan Wang, Xiaocong Li, Lihao Zheng, Adrish Bhaumik, Prahlad Vadakkepat

机构 * National University of Singapore（新加坡国立大学） ； SIMTech, A*STAR ； CUHK, Shenzhen（香港中文大学（深圳）） 纠错

专题命中 具身导航 ：robotics(abstract,comments)；分类 cs.RO、cs.AI

AI总结 本文提出SafeCtrlBO方法，通过加性高斯过程核减少样本复杂度，实现多耦合控制器的同时优化，实验显示在较少硬件评估下达到高性能参数并保证安全。

Comments The shorter version has been accepted by IEEE Robotics and Automation Letters. This is the full version

Value Explicit Pretraining for Learning Transferable Representations

为学习可迁移的表示进行价值显式预训练

Kiran Lekkala, Henghui Bao, Sumedh A. Sontakke, Erdem Biyik, Laurent Itti

机构 * Thomas Lord Department of Computer Science at the University of Southern California（南加州大学汤姆·劳德计算机科学系） 纠错

专题命中 具身导航 ：navigation(abstract)；分类 cs.RO、cs.LG；robotics(comments)

AI总结 本文提出价值显式预训练（VEP），通过学习对环境动态和外观变化不变的表示，提升强化学习任务迁移能力。实验表明VEP在未见任务泛化能力、奖励和样本效率上均优于现有方法。

Comments Published in Robotics and Automation Letters (RA-L), January 2026

Dynamic UGV-UAV Cooperative Path Planning in Uncertain Environments

动态不确定环境中UGV-UAV协同路径规划

Ninh Nguyen, Srinivas Akella

机构 * Department of Computer Science, University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校计算机科学系） 纠错

专题命中 具身导航 ：navigation(abstract)；分类 cs.RO、cs.AI；robotics(comments)

AI总结 本文提出动态UGV-UAV协同路径规划方法，通过无人机动态检测道路以提高地面车辆路径安全性与效率，实验表明双向策略在多数情况下表现最佳，多无人机可减少地面车辆行驶时间但增加计算时间。

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

MCGS-SLAM: A Multi-Camera SLAM Framework Using Gaussian Splatting for High-Fidelity Mapping

MCGS-SLAM：一种基于高斯点划的多相机SLAM框架用于高保真的地图构建

Zhihao Cao, Hanyu Wu, Li Wa Tang, Zizhou Luo, Wei Zhang, Marc Pollefeys, Zihan Zhu, Martin R. Oswald

机构 * Department of Mathematics, ETH Zurich（苏黎世联邦理工学院数学系） ； Department of Mechanical and Process Engineering, ETH Zurich（苏黎世联邦理工学院机械与工艺工程系） ； Department of Informatics, University of Zurich（苏黎世大学信息系） ； Institute for Photogrammetry, University of Stuttgart（斯图加特大学摄影测量研究所） ； Computer Vision and Geometry Group, ETH Zurich（苏黎世联邦理工学院计算机视觉与几何组） ； Microsoft Spatial AI Lab（微软空间AI实验室） ； Computer Vision Research Group, University of Amsterdam（阿姆斯特丹大学计算机视觉研究组） 纠错

专题命中 具身导航 ：robotics(abstract,comments)；分类 cs.RO、cs.CV

AI总结 MCGS-SLAM通过多相机和高斯点划技术实现高保真的SLAM，提供精确轨迹和逼真重建，优于单目方法。

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

Learning Physical Systems: Symplectification via Gauge Fixing in Dirac Structures

学习物理系统：通过Dirac结构进行配分的配分

Aristotelis Papatheodorou, Pranav Vaidhyanathan, Natalia Ares, Ioannis Havoutis

机构 * Department of Engineering Science, University of Oxford（牛津大学工程科学系） 纠错

专题命中 具身导航 ：robotics(abstract,comments)；分类 cs.RO、cs.LG

AI总结 本文提出预配分网络（PSNs），通过Dirac结构学习配分提升，恢复非退化对称几何，实现受约束耗散系统的几何机器学习模型。

Comments Presented at Equivariant Systems: Theory and Applications in State Estimation, Artificial Intelligence and Control, Robotics: Science and Systems (RSS) 2025 Workshop, 6 Pages, 3 Figures

Enhancing Supermarket Robot Interaction: A Multi-Level LLM Conversational Interface for Handling Diverse Customer Intents

增强超市机器人交互：一种多层级LLM对话接口用于处理多样化客户意图

Chandran Nandkumar, Luka Peternel

机构 * Delft University of Technology（代尔夫特理工大学） 纠错

专题命中 具身导航 ：navigation(abstract)；分类 cs.RO、cs.AI；robotics(journal_ref)

AI总结 本文提出多层级LLM接口提升超市机器人处理多样化客户意图的效率与性能。

Journal ref Frontiers in Robotics and AI, Volume 12, 1576348, April 2025

MoonBot: Modular and On-Demand Reconfigurable Robot Toward Moon Base Construction

MoonBot：模块化和按需重构机器人用于月球基地建设

Kentaro Uno, Elian Neppel, Gustavo H. Diaz, Ashutosh Mishra, Shamistan Karimov, A. Sejal Jain, Ayesha Habib, Pascal Pama, Hazal Gozbasi, Shreya Santra, Kazuya Yoshida

机构 * Tohoku University（东北大学） 纠错

专题命中 具身导航 ：robotic(abstract)；分类 cs.RO、cs.AI；robotics(comments)

AI总结 MoonBot是一种模块化和按需重构机器人，旨在通过执行模拟月球基础设施建设的任务来支持月球基地建设。

Comments This is the authors' version of a paper accepted for publication in IEEE Transactions on Field Robotics, (c) IEEE. The final published version is available at https://doi.org/10.1109/TFR.2025.3624346

Event Spectroscopy: Event-based Multispectral and Depth Sensing using Structured Light

事件光谱：基于事件的多光谱和深度感知使用结构光

Christian Geckeler, Niklas Neugebauer, Manasi Muglikar, Davide Scaramuzza, Stefano Mintchev

机构 * Environmental Robotics Laboratory, Dep. of Environmental Systems Science, ETH Zurich（环境机器人实验室，环境系统科学系，苏黎世联邦理工学院） ； Swiss Federal Institute for Forest, Snow and Landscape Research (WSL)（瑞士森林、雪和景观研究联邦研究所） ； Robotics and Perception Group, University of Zurich（机器人与感知小组，苏黎世大学） 纠错

专题命中 具身导航 ：navigation(abstract)；分类 cs.RO、cs.CV；robotics(comments)

AI总结 本研究提出了一种基于事件的多光谱和深度感知系统，利用结构光实现高分辨率、低延迟的深度重建和多光谱成像，在森林环境中提升UAV的感知与数据收集能力。

Comments This work has been accepted for publication in IEEE Robotics and Automation Letters

Feedback-MPPI: Fast Sampling-Based MPC via Rollout Differentiation -- Adios low-level controllers

反馈-MPPI: 通过轨迹微分实现快速采样-based MPC -- Adios低级控制器

Tommaso Belvedere, Michael Ziegltrum, Giulio Turrisi, Valerio Modugno

专题命中 具身导航 ：robotic(abstract)；分类 cs.RO、cs.AI；robotics(journal_ref)

AI总结 Feedback-MPPI通过局部反馈增益提升MPPI性能，实现高频稳定控制，适用于复杂机器人系统。

Journal ref IEEE Robotics and Automation Letters, 2026, 11 (1), pp.1 - 8

MGSO: Monocular Real-time Photometric SLAM with Efficient 3D Gaussian Splatting

Yan Song Hu, Nicolas Abboud, Muhammad Qasim Ali, Adam Srebrnjak Yang, Imad Elhajj, Daniel Asmar, Yuhao Chen, John S. Zelek

机构 * Vision and Image Processing Lab at the Faculty of System Design Engineering, at the University of Waterloo（视觉与图像处理实验室，系统设计工程学院，滑铁卢大学） ； Vision and Robotics Lab, Maroun Semaan Faculty of Engineering and Architecture, American University of Beirut（视觉与机器人实验室，马鲁恩·塞马安工程与建筑学院，贝鲁特美国大学） 纠错

专题命中 具身导航 ：robotics(abstract,journal_ref)；分类 cs.RO、cs.CV

Comments This is the pre-print version of a work that has been published in ICRA 2025 with doi: 10.1109/ICRA55743.2025.11127380. This version may no longer be accessible without notice. Copyright 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses. Please cite the official version

Journal ref 2025 IEEE International Conference on Robotics and Automation (ICRA), Atlanta, GA, USA, 2025, pp. 11061-11067

Data-Driven Predictive Control of Nonholonomic Robots Based on a Bilinear Koopman Realization: Data Does Not Replace Geometry

Mario Rosenfelder, Lea Bold, Hannes Eschmann, Peter Eberhard, Karl Worthmann, Henrik Ebel

机构 * Institute of Engineering and Computational Mechanics (ITM), University of Stuttgart（工程与计算力学研究所（ITM），斯图加特大学） ； Optimization-based Control Group, Institute of Mathematics, Technische Universität Ilmenau（优化控制组，数学研究所，伊尔梅瑙技术大学） ； Department of Mechanical Engineering, LUT University（机械工程系，卢托大学） 纠错

专题命中 具身导航 ：robotics(abstract,journal_ref)；分类 cs.RO、cs.LG

Comments 23 pages, 12 figures

Journal ref Robotics and Autonomous Systems, Volume 194, 105156, 2025

LPAC: Learnable Perception-Action-Communication Loops with Applications to Coverage Control

Saurav Agarwal, Ramya Muthukrishnan, Walker Gosrich, Vijay Kumar, Alejandro Ribeiro

机构 * GRASP Laboratory, University of Pennsylvania（宾夕法尼亚大学GRASP实验室） ； Massachusetts Institute of Technology（麻省理工学院） ； University of Pennsylvania（宾夕法尼亚大学） ； Department of Electrical and Systems Engineering, University of Pennsylvania（宾夕法尼亚大学电气与系统工程系） 纠错

专题命中 具身导航 ：navigation(abstract)；分类 cs.RO、cs.LG；robotics(journal_ref)

Comments 20 Pages, 20 figures,

Journal ref in IEEE Transactions on Robotics, vol. 41, pp. 5986-6005, 2025

Autonomous 3D Exploration in Large-Scale Environments with Dynamic Obstacles

Emil Wiman, Ludvig Widén, Mattias Tiger, Fredrik Heintz

专题命中 具身导航 ：robotics(abstract,journal_ref)；分类 cs.RO、cs.AI

Comments 6 pages, 6 figures

Journal ref 2024 IEEE International Conference on Robotics and Automation (ICRA), Yokohama, Japan, 2024, pp. 2389-2395,

A Parameter-Efficient Mixture-of-Experts Framework for Cross-Modal Geo-Localization

LinFeng Li, Jian Zhao, Zepeng Yang, Yuhang Song, Bojun Lin, Tianle Zhang, Yuchen Yuan, Chi Zhang, Xuelong Li

机构 * The Institute of Artificial Intelligence (TeleAI), China Telecom（人工智能研究所（TeleAI），中国电信） ； East China Normal University（东华师范大学） ； National Tsing Hua University（国立清华大学） 纠错

专题命中 具身导航 ：navigation(abstract,journal_ref)；分类 cs.AI、cs.CV

Journal ref IROS 2025 Robosense Cross-Modal Drone Navigation Challenge first place

Self-supervised Multi-future Occupancy Forecasting for Autonomous Driving

Bernard Lange, Masha Itkina, Jiachen Li, Mykel J. Kochenderfer

专题命中 具身导航 ：navigation(abstract)；分类 cs.RO、cs.CV；robotics(comments)

Comments Accepted to Robotics: Science and Systems (RSS) 2025

Online Mapping for Autonomous Driving: Addressing Sensor Generalization and Dynamic Map Updates in Campus Environments

Zihan Zhang, Abhijit Ravichandran, Pragnya Korti, Luobin Wang, Henrik I. Christensen

机构 * University of California, San Diego（加州大学圣地亚哥分校） 纠错

专题命中 具身导航 ：navigation(abstract)；分类 cs.RO、cs.CV；robotics(comments)

Comments 19th International Symposium on Experimental Robotics

STHN: Deep Homography Estimation for UAV Thermal Geo-localization with Satellite Imagery

Jiuhong Xiao, Ning Zhang, Daniel Tortei, Giuseppe Loianno

机构 * New York University（纽约大学） ； Autonomous Robotics Research Center-Technology Innovation Institute（自主机器人研究中心-技术创新研究所） 纠错

专题命中 具身导航 ：navigation(abstract)；分类 cs.RO、cs.CV；robotics(comments)

Comments 8 pages, 7 figures. Accepted for IEEE Robotics and Automation Letters

Learn to Swim: Data-Driven LSTM Hydrodynamic Model for Quadruped Robot Gait Optimization

Fei Han, Pengming Guo, Hao Chen, Weikun Li, Jingbo Ren, Naijun Liu, Ning Yang, Dixia Fan

机构 * Zhejiang University（浙江大学） ； FSI lab, Westlake University（西湖大学FSI实验室） ； Xinyang Normal University（新阳师范学院） ； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） 纠错

专题命中 具身导航 ：robotic(abstract)；分类 cs.RO、cs.LG；robotics(comments)

Comments This work has been accepted for publication in the IEEE International Conference on Robotics and Automation (ICRA) 2025. The final version will be available in IEEE Xplore (DOI to be assigned upon publication)

DVM-SLAM: Decentralized Visual Monocular Simultaneous Localization and Mapping for Multi-Agent Systems

Joshua Bird, Jan Blumenkamp, Amanda Prorok

机构 * Department of Computer Science and Technology, University of Cambridge（计算机科学与技术系，剑桥大学） 纠错

专题命中 具身导航 ：navigation(abstract)；分类 cs.RO、cs.CV；robotics(comments)

Comments Accepted to 2025 IEEE International Conference on Robotics and Automation, pp. 15814-15820

DRIVE Through the Unpredictability:From a Protocol Investigating Slip to a Metric Estimating Command Uncertainty

Nicolas Samson, William Larrivée-Hardy, William Dubois, Élie Roy-Brouard, Edith Brotherton, Dominic Baril, Julien Lépine, François Pomerleau

专题命中 具身导航 ：navigation(abstract)；分类 cs.RO、cs.LG；robotics(comments)

Comments This version is the preprint of a journal article with the same title, accepted in the IEEE Transactions on Field Robotics. To have a look at the early access version, use the following link https://ieeexplore.ieee.org/document/11037776

End-to-End Framework for Robot Lawnmower Coverage Path Planning using Cellular Decomposition

Nikunj Shah, Utsav Dey, Kenji Nishimiya

机构 * Honda R&D Co., Ltd.（本田技研控股有限公司） 纠错

专题命中 具身导航 ：robotic(abstract)；分类 cs.RO、cs.AI；robotics(comments)

Comments 8 pages, ICRA 2025, Workshop on Field Robotics

Towards Global Localization using Multi-Modal Object-Instance Re-Identification

Aneesh Chavan, Vaibhav Agrawal, Vineeth Bhat, Sarthak Chittawar, Siddharth Srivastava, Chetan Arora, K Madhava Krishna

机构 * RRC, IIIT Hyderabad India（IIIT Hyderabad 印度研究院） ； TypeFace Inc. India（印度 Typeface 公司） 纠错

专题命中 具身导航 ：robotic(abstract)；分类 cs.RO、cs.CV；robotics(comments)

Comments 8 pages, 5 figures, 3 tables. Accepted at Advances in Robotics, AIR 2025 (Oral)

Deep-Learning Control of Lower-Limb Exoskeletons via simplified Therapist Input

Lorenzo Vianello, Clément Lhoste, Emek Barış Küçüktabak, Matthew Short, Levi Hargrove, Jose L. Pons

专题命中 具身导航 ：navigation(abstract)；分类 cs.RO、cs.LG；robotics(comments)

Comments Accepted to the INTERNATIONAL CONSORTIUM FOR REHABILITATION ROBOTICS 2025

ActiveGS: Active Scene Reconstruction Using Gaussian Splatting

Liren Jin, Xingguang Zhong, Yue Pan, Jens Behley, Cyrill Stachniss, Marija Popović

专题命中 具身导航 ：robotics(abstract,comments)；分类 cs.RO、cs.CV

Comments Accepted to IEEE Robotics and Automation Letters

ForestVO: Enhancing Visual Odometry in Forest Environments through ForestGlue

Thomas Pritchard, Saifullah Ijaz, Ronald Clark, Basaran Bahadir Kocer

机构 * Imperial College London（帝国理工学院） ； University of Oxford（牛津大学） ； University of Bristol（布里斯托大学） 纠错

专题命中 具身导航 ：navigation(abstract)；分类 cs.RO、cs.CV；robotics(comments)

Comments Accepted to the IEEE Robotics and Automation Letters

Why Autonomous Vehicles Are Not Ready Yet: A Multi-Disciplinary Review of Problems, Attempted Solutions, and Future Directions

Xingshuai Dong, Max Cappuccio, Hamad Al Jassmi, Fady Alnajjar, Essam Debie, Milad Ghasrikhouzani, Alessandro Lanteri, Ali Luqman, Tate McGregor, Oleksandra Molloy, Alice Plebe, Michael Regan, Dongmo Zhang

专题命中 具身导航 ：navigation(abstract)；分类 cs.RO、cs.CV；robotics(comments)

Comments This manuscript extends the work "Applications of Computer Vision in Autonomous Vehicles: Methods, Challenges, and Future Directions." We have added several sections to explore autonomous vehicles from a multidisciplinary perspective. We propose changing the arXiv category to cs.RO, as the expanded content addresses broader autonomous vehicle topics aligning more closely with the Robotics domain

UGNA-VPR: A Novel Training Paradigm for Visual Place Recognition Based on Uncertainty-Guided NeRF Augmentation

Yehui Shen, Lei Zhang, Qingqiu Li, Xiongwei Zhao, Yue Wang, Huimin Lu, Xieyuanli Chen

机构 * College of Intelligence Science and Technology, National University of Defense Technology（国防科技大学智能科学学院） ； Faculty of Robot Science and Engineering, Northeastern University（东北大学机器人科学与工程学院） ； School of Electronic and Information Engineering, Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）电子与信息工程学院） ； Institute of Cyber-Systems and Control, Zhejiang University（浙江大学网络系统与控制研究所） ； SIASUN Robot& Automation Co., Ltd（新松机器人自动化股份有限公司） ； School of Computer Science, Fudan University（复旦大学计算机科学技术学院） 纠错

专题命中 具身导航 ：navigation(abstract)；分类 cs.RO、cs.CV；robotics(comments)

Comments Accepted to IEEE Robotics and Automation Letters (RA-L)