机器人 / 具身智能

Language-guided Semantic Mapping and Mobile Manipulation in Partially Observable Environments

Siddharth Patki, Ethan Fahnestock, Thomas M. Howard, Matthew R. Walter

专题命中 具身导航 ：manipulation(title)；分类 cs.RO、cs.AI；robot learning(comments)

Comments To appear at 2019 Conference on Robot Learning (CoRL)

Chain of Spatial Thoughts: Modality-Agnostic Spatial Grounding for Vision Language Models

空间思维链：面向视觉语言模型的模态无关空间定位

Hunter Schofield, Mohammed Elmahgiubi, Mohammad Mahdavian, Richard Shi, Jinjun Shan, Amir Rasouli, Dongfeng Bai

专题命中 具身导航 ：manipulation(abstract)；navigation(abstract)；robotic(abstract)；分类 cs.CV

AI总结 该研究提出轻量架构无关框架Space Tokens，将空间信息蒸馏为连续token融入VLMs的思维链，在VSI-Bench上提升两款模型性能，在尺寸估计任务达SOTA，实现高效空间推理。

A Generative Partially Specified Finite State Machine Approach to Complex Behaviour Planning

一种用于复杂行为规划的生成式部分指定有限状态机方法

Kalana Ratnayake, Michael Pritchard, David Hinwood, Maleen Jayasuriya, Damith Herath

机构 * University of Canberra（堪培拉大学） 纠错

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

AI总结 研究为自主机器人在动态环境中的行为规划，提出生成式部分指定有限状态机（GPSFSM）神经符号架构，利用Fabric等组件实现标准化语义能力描述，实验表明该方法计划生成成功率高、延迟低，还能生成复杂行为，且开源堆栈使其实用可重复。

Comments Accepted for publication in the 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 9 pages, 10 figures, 1 table

GeoGS-SLAM: Geometry-Only Gaussian Splatting for Dense Monocular SLAM

GeoGS-SLAM：用于密集单目 SLAM 的仅几何高斯点云法

Lipu Zhou, Yaoyun Kang, Junxiang Pang, Shengkai Sun, Tingting Bao, Kehan Wang

机构 * School of Instrument Science and Opto-electronics Engineering, Beihang University（仪器科学与光电工程学院，北京航空航天大学） 纠错

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

AI总结 研究针对密集视觉 SLAM 问题，提出仅几何高斯点云法（GeoGS）及基于此的 GeoGS-SLAM 系统。该方法仅保留空间参数减少基元参数，专注几何重建，通过有效训练框架和地图更新策略，提升在线映射效率与几何重建质量。

Beyond Pure Sampling: Hybrid Optimization Mechanisms for Non-Convex Model Predictive Control

超越纯采样：非凸模型预测控制的混合优化机制

Yuichiro Aoyama, Minchan Jung, Akash Ratheesh, Evangelos A. Theodorou

机构 * School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA, USA（航空航天工程学院，佐治亚理工学院，美国亚特兰大，GA州） ； Development Division, Komatsu Ltd., Tokyo, Japan（Komatsu Ltd.开发部门，日本东京） ； Department of Electrical and Computer Engineering, Inha University, Incheon, Republic of Korea（电气与计算机工程系，inha大学，韩国仁川，大韩民国） 纠错

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

AI总结 本文提出一种结合梯度下降与基于逆Hessian采样的双步优化机制，用于非凸模型预测控制，在多种机器人导航任务中相比纯采样方法（如MPPI）具有更高成功率和稳定性。

Comments 28 pages, 13 figures

Enhancing Vision-Based Policies with Omni-View and Cross-Modality Knowledge Distillation for Mobile Robots

通过多视角与跨模态知识蒸馏增强基于视觉的策略用于移动机器人

Kai Li, Shiyu Zhao

机构 * College of Computer Science and Technology at Zhejiang University（浙江大学计算机科学与技术学院） ； School of Engineering at Westlake University（西湖大学工程学院） 纠错

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

AI总结 本文提出通过多视角和跨模态知识蒸馏提升移动机器人基于视觉的策略，解决场景迁移性差、计算资源有限和传感器成本高等问题。

OGScene3D: Incremental Open-Vocabulary 3D Gaussian Scene Graph Mapping for Scene Understanding

OGScene3D: 增量式开放词汇3D高斯场景图映射用于场景理解

Siting Zhu, Ziyun Lu, Guangming Wang, Chenguang Huang, Yongbo Chen, I-Ming Chen, Wolfram Burgard, Hesheng Wang

机构 * Shanghai Jiao Tong University（上海交通大学） ； University of Cambridge（剑桥大学） ； University of Technology Nuremberg（纽伦堡技术大学） ； Nanyang Technological University（南洋理工大学） ； Department of Automation, Key Laboratory of System Control and Information Processing of Ministry of Education, State Key Laboratory of Avionics Integration and Aviation System-of-Systems Synthesis, Shanghai Key Laboratory of Navigation and Location Based Services, Shanghai Jiao Tong University（自动化系，教育部系统控制与信息处理重点实验室，航空系统集成与航空系统-of-系统综合国家重点实验室，上海导航与定位基于服务重点实验室，上海交通大学） 纠错

专题命中 具身导航 ：manipulation(abstract)；navigation(abstract)；robotic(abstract)；分类 cs.RO

AI总结 OGScene3D通过增量式3D高斯场景图映射，实现开放词汇场景理解，结合高斯表示与层次优化策略，提升语义一致性与长期优化能力。

Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration

视觉到几何：用于连续具身MLLM推理和探索的3D空间记忆

Zhongyi Cai, Yi Du, Chen Wang, Yu Kong

机构 * ACTION Lab, Michigan State University（密歇根州立大学ACTION实验室） ； SAIR Lab, University at Buffalo（布法罗大学SAIR实验室） 纠错

专题命中 具身导航 ：embodied AI(abstract)；embodied agent(abstract)；navigation(abstract)；分类 cs.CV

AI总结 本文提出3DSPMR框架，利用视场覆盖作为几何先验，提升具身智能在连续任务中的记忆、推理与探索能力，并引入SEER-Bench基准测试连续具身探索与推理任务。

Comments Computer Vision

Design and Control of Modular Magnetic Millirobots for Multimodal Locomotion and Shape Reconfiguration

模块化磁性微机器人多模态运动与形状重构设计与控制

Erik Garcia Oyono, Jialin Lin, Dandan Zhang

机构 * Department of Bioengineering, Imperial College London（帝国理工学院生物工程系） 纠错

专题命中 具身导航 ：manipulation(abstract)；navigation(abstract)；robotic(abstract)；分类 cs.RO

AI总结 本研究提出一种模块化磁性微机器人平台，通过多模块协同实现多模态运动与形状重构，展示了在受限环境中稳健控制的潜力。

Comments Accepted by 2026 ICRA

Interactive LLM-assisted Curriculum Learning for Multi-Task Evolutionary Policy Search

多任务策略搜索中的交互式LLM辅助课程学习

Berfin Sakallioglu, Giorgia Nadizar, Eric Medvet

机构 * MIGe - University of Trieste（MIGe - 乌迪内大学） ； University Toulouse Capitole, IRIT - CNRS UMR5505（图卢兹大学，IRIT - CNRS UMR5505） ； DIA - University of Trieste（DIA - 乌迪内大学） 纠错

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

AI总结 本文提出了一种交互式LLM辅助的在线课程生成框架，通过多模态反馈提升多任务策略搜索的性能，展示其与专家设计课程的竞争力。

Comments 8 pages, 7 figures, with Appendix

Sistema de navegación de cobertura para vehículos no holonómicos en ambientes de exterior

非holonomic车辆在外环境中的覆盖导航系统

Michelle Valenzuela, Francisco Leiva, Javier Ruiz-del-Solar

机构 * Advanced Mining Technology Center, Universidad de Chile（先进采矿技术中心，智利大学） ； Departamento de Ingeniería Eléctrica, Universidad de Chile（电气工程系，智利大学） 纠错

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

AI总结 本文提出了一种非holonomic车辆的覆盖导航系统，用于在真实和模拟户外环境中实现高效地形覆盖，通过动态障碍物处理和恢复行为提升自动化水平。

Comments 13 pages, in Spanish language, 12 figures, accepted at Tercer Congreso Iberoamericano de Minería Subterranea y a Cielo Abierto, UMining 2024

TongSIM: A General Platform for Simulating Intelligent Machines

TongSIM: 一个用于模拟智能机器的通用平台

Zhe Sun, Kunlun Wu, Chuanjian Fu, Zeming Song, Langyong Shi, Zihe Xue, Bohan Jing, Ying Yang, Xiaomeng Gao, Aijia Li, Tianyu Guo, Huiying Li, Xueyuan Yang, Rongkai Liu, Xinyi He, Yuxi Wang, Yue Li, Mingyuan Liu, Yujie Lu, Hongzhao Xie, Shiyun Zhao, Bo Dai, Wei Wang, Tao Yuan, Song-Chun Zhu, Yujia Peng, Zhenliang Zhang

机构 * State Key Laboratory of General Artificial Intelligence（通用人工智能国家重点实验室） ； BIGAI ； Beijing, China（中国北京） 纠错

专题命中 具身导航 ：embodied AI(abstract)；embodied agent(abstract)；navigation(abstract)；分类 cs.AI

AI总结 TongSIM是一个通用平台，用于训练和评估具身智能代理，提供多样化的场景和交互丰富的环境，支持从低级导航到高级复合活动的广泛研究需求。

Robust and Modular Multi-Limb Synchronization in Motion Stack for Space Robots with Trajectory Clamping via Hypersphere

在空间机器人运动堆栈中通过超球体实现鲁棒且模块化的多肢体同步

Elian Neppel, Ashutosh Mishra, Shamistan Karimov, Kentaro Uno, Shreya Santra, Kazuya Yoshida

机构 * Space Robotics Lab. (SRL) in Department of Aerospace Engineering, Graduate School of Engineering, Tohoku University（太空机器人实验室（SRL）位于东京东京大学工学研究生院航空航天工程系） 纠错

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

AI总结 本研究提出了一种通过超球体约束实现鲁棒多肢体同步的方法，适用于空间机器人运动堆栈的模块化协调。

Comments 6 pages, 15 figures. Accepted at IROS 2025 | Video: https://youtu.be/hr_kUrbqnFg | Open source project: http://motion-stack.deditoolbox.fr | Code: https://github.com/2lian/Motion-Stack

Journal ref 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Pages 3767-3772

APEX: Action Priors Enable Efficient Exploration for Robust Motion Tracking on Legged Robots

Shivam Sood, Laukik Nakhwa, Sun Ge, Yuhong Cao, Jin Cheng, Fatemah Zargarbashi, Taerim Yoon, Sungjoon Choi, Stelian Coros, Guillaume Sartoretti

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

Comments This work was intended as a replacement of arXiv:2505.10022 and any subsequent updates will appear there

An Open-Source, Reproducible Tensegrity Robot that can Navigate Among Obstacles

William R. Johnson, Patrick Meng, Nelson Chen, Luca Cimatti, Augustin Vercoutere, Mridul Aanjaneya, Rebecca Kramer-Bottiglio, Kostas E. Bekris

机构 * Y Mech. Eng., Yale Univ.（耶鲁大学机械工程系） ； R Comp. Sc., Rutgers Univ.（罗格斯大学计算机科学系） 纠错

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

Embodied Intelligence for Advanced Bioinspired Microrobotics: Examples and Insights

Nestor O. Perez-Arancibia

机构 * Washington State University (WSU)（华盛顿州立大学） 纠错

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

Comments 8 pages, 7 figures, accepted to ICAR 2025

Dual-Stage Safe Herding Framework for Adversarial Attacker in Dynamic Environment

Wenqing Wang, Ye Zhang, Haoyu Li, Jingyu Wang

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

Elliptical K-Nearest Neighbors -- Path Optimization via Coulomb's Law and Invalid Vertices in C-space Obstacles

Liding Zhang, Zhenshan Bing, Yu Zhang, Kuanqi Cai, Lingyun Chen, Fan Wu, Sami Haddadin, Alois Knoll

机构 * Department of Informatics, Technical University of Munich（信息学院，慕尼黑技术大学） 纠错

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

Comments 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Real-Time 3D Vision-Language Embedding Mapping

Christian Rauch, Björn Ellensohn, Linus Nwankwo, Vedant Dave, Elmar Rueckert

机构 * Technical University of Leoben（莱博恩技术大学） 纠错

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

GS-I$^{3}$: Gaussian Splatting for Surface Reconstruction from Illumination-Inconsistent Images

Tengfei Wang, Xin Wang, Yongmao Hou, Zhaoning Zhang, Yiwei Xu, Zongqian Zhan

机构 * School of Geodesy and Geomatics, Wuhan University（武汉大学测绘学院） 纠错

专题命中 具身导航 ：manipulation(abstract)；navigation(abstract)；robotic(abstract)；分类 cs.CV

Decentralized Nonlinear Model Predictive Control-Based Flock Navigation with Real-Time Obstacle Avoidance in Unknown Obstructed Environments

Nuthasith Gerdpratoom, Kaoru Yamamoto

专题命中 具身导航 ：navigation(title)；robotics(comments,journal_ref)；分类 cs.RO

Comments 22 pages, 14 figures, to be published in Frontiers in Robotics and AI

Journal ref Frontiers in Robotics and AI, Vol. 12, 2025

NanoSLAM: Enabling Fully Onboard SLAM for Tiny Robots

Vlad Niculescu, Tommaso Polonelli, Michele Magno, Luca Benini

机构 * Integrated Systems Laboratory of ETH Zürich（苏黎世联邦理工学院集成系统实验室） ； Center for Project-Based Learning of ETH Zürich（苏黎世联邦理工学院项目导向学习中心） ； Department of Electrical, Electronic and Information Engineering of University of Bologna（博洛尼亚大学电子、电子与信息工程系） 纠错

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

Comments 24 pages

Leveraging Symmetry in RL-based Legged Locomotion Control

Zhi Su, Xiaoyu Huang, Daniel Ordoñez-Apraez, Yunfei Li, Zhongyu Li, Qiayuan Liao, Giulio Turrisi, Massimiliano Pontil, Claudio Semini, Yi Wu, Koushil Sreenath

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

Journal ref 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 6899-6906

TeTRA-VPR: A Ternary Transformer Approach for Compact Visual Place Recognition

Oliver Grainge, Michael Milford, Indu Bodala, Sarvapali D. Ramchurn, Shoaib Ehsan

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

RobotIQ: Empowering Mobile Robots with Human-Level Planning for Real-World Execution

Emmanuel K. Raptis, Athanasios Ch. Kapoutsis, Elias B. Kosmatopoulos

专题命中 具身导航 ：manipulation(abstract)；navigation(abstract)；robotic(abstract)；分类 cs.RO

Augmented Environment Representations with Complete Object Models

Krishnananda Prabhu Sivananda, Francesco Verdoja, Ville Kyrki

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

Comments Accepted for publication in the 31st IEEE International Conference on Robot & Human Interactive Communication (RO-MAN 2022)

Journal ref 2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), Aug. 2022, pp. 1123-1130

Active Semantic Mapping with Mobile Manipulator in Horticultural Environments

Jose Cuaran, Kulbir Singh Ahluwalia, Kendall Koe, Naveen Kumar Uppalapati, Girish Chowdhary

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

Comments Preprint (under review)

Conjugate Momentum-Based Estimation of External Forces for Bio-Inspired Morphing Wing Flight

Bibek Gupta, Eric Sihite, Alireza Ramezani

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

Embedding Pose Graph, Enabling 3D Foundation Model Capabilities with a Compact Representation

Hugues Thomas, Mouli Sivapurapu, Jian Zhang

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

Understanding Generative AI in Robot Logic Parametrization

Yuna Hwang, Arissa J. Sato, Pragathi Praveena, Nathan Thomas White, Bilge Mutlu

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

Comments 5 pages, 2 figures. Paper presented at the End-User Development for Human-Robot Interaction (EUD4HRI) Workshop, part of the 19th Annual ACM/IEEE International Conference on Human Robot Interaction (HRI, 2024)