机器人 / 具身智能

Constrained Robotic Navigation on Preferred Terrains Using LLMs and Speech Instruction: Exploiting the Power of Adverbs

Faraz Lotfi, Farnoosh Faraji, Nikhil Kakodkar, Travis Manderson, David Meger, Gregory Dudek

专题命中 具身导航 ：navigation(title,abstract)；robotic(title)；分类 cs.RO、cs.LG

Comments Presented at ISER 2023

Learned Perceptive Forward Dynamics Model for Safe and Platform-aware Robotic Navigation

Pascal Roth, Jonas Frey, Cesar Cadena, Marco Hutter

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

Comments To be published in the proceedings of Robotics: Science and Systems (RSS) 2025

Grow-Prune-Freeze Networks: Adaptive & Continual Learning Technique for Olfactory Navigation

生长-剪枝-冻结网络：用于嗅觉导航的自适应与持续学习技术

Kordel K. France, Ovidiu Daescu

专题命中 具身导航 ：navigation(title,abstract)；robotics(abstract)；world model(abstract)；分类 cs.RO、cs.AI、cs.LG

AI总结 提出生长-剪枝-冻结（GPF）网络框架，通过动态调整策略网络层数实现持续学习，在湍流羽流导航任务中达到94%成功率，并推广到其他机器学习任务。

Comments Accepted as poster to the Reinforcement Learning in Big Worlds Workshop at the 2026 Reinforcement Learning Conference

Reasoning in visual navigation of end-to-end trained agents: a dynamical systems approach

Steeven Janny, Hervé Poirier, Leonid Antsfeld, Guillaume Bono, Gianluca Monaci, Boris Chidlovskii, Francesco Giuliari, Alessio Del Bue, Christian Wolf

专题命中 具身导航 ：navigation(title,abstract)；robotics(abstract)；embodied AI(abstract)；分类 cs.RO、cs.CV、cs.LG

Journal ref Computer Vision and Pattern Recognition Conference (CVPR) 2025

ViNT: A Foundation Model for Visual Navigation

Dhruv Shah, Ajay Sridhar, Nitish Dashora, Kyle Stachowicz, Kevin Black, Noriaki Hirose, Sergey Levine

专题命中 具身导航 ：navigation(title,abstract)；robotics(abstract)；robotic(abstract)；分类 cs.RO、cs.CV、cs.LG

Comments Accepted for oral presentation at CoRL 2023

What do navigation agents learn about their environment?

Kshitij Dwivedi, Gemma Roig, Aniruddha Kembhavi, Roozbeh Mottaghi

专题命中 具身导航 ：navigation(title,abstract)；embodied AI(abstract)；embodied agent(abstract)；分类 cs.RO、cs.CV、cs.LG

Comments CVPR 2022

Image-based Geo-localization for Robotics: Are Black-box Vision-Language Models there yet?

基于图像的机器人地理定位：黑盒视觉语言模型是否已经足够？

Sania Waheed, Bruno Ferrarini, Michael Milford, Sarvapali D. Ramchurn, Shoaib Ehsan

机构 * University of Southampton（南安普顿大学） ； MyWay srl ； Queensland University of Technology（昆士兰科技大学） ； University of Essex（埃塞克斯大学） 纠错

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

AI总结 本文首次系统研究黑盒生成式视觉语言模型作为独立零样本地理定位系统的潜力，发现其在粗粒度定位上表现良好，但在细粒度定位上因现实变化而显著退化。

Comments Accepted to the ICRA 2026 Workshop on Multi-Modal Spatial AI for Robust Navigation and Open-World Understanding (MM-SpatialAI)

Enhancing Autonomous Navigation by Imaging Hidden Objects using Single-Photon LiDAR

Aaron Young, Nevindu M. Batagoda, Harry Zhang, Akshat Dave, Adithya Pediredla, Dan Negrut, Ramesh Raskar

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

Comments Project webpage: https://camera-culture.github.io/nlos-aided-autonomous-navigation

A Deep Learning Driven Algorithmic Pipeline for Autonomous Navigation in Row-Based Crops

Simone Cerrato, Vittorio Mazzia, Francesco Salvetti, Mauro Martini, Simone Angarano, Alessandro Navone, Marcello Chiaberge

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

Comments Submitted to Robotics and Autonomous Systems (Elsevier)

Extending Maps with Semantic and Contextual Object Information for Robot Navigation: a Learning-Based Framework using Visual and Depth Cues

Renato Martins, Dhiego Bersan, Mario F. M. Campos, Erickson R. Nascimento

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

Comments Preprint version of the article to appear at Journal of Intelligent & Robotic Systems (2020)

HyperDCM: Dynamic Cluster Memory Replay in Hyperbolic Space for Continual Robotic Navigation Across Scenes

HyperDCM：用于跨场景连续机器人导航的双曲空间动态集群记忆回放

Zhengfei Lu, Jian Yang, Muyu Wang, Shaowen Chen, Jinpeng Mi, Ke Li, Xiong You, Qi Wu, Xuan Tang, Xian Wei

机构 * Software Engineering Institute, East China Normal University（华东师范大学软件工程学院） ； School of Geospatial Information, Information Engineering University（信息工程大学地理空间信息学院） ； University of Shanghai for Science and Technology（上海理工大学） ； Shanghai Jiao Tong University（上海交通大学） 纠错

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

AI总结 针对视觉导航持续学习难题，提出HyperDCM，通过场景图建模和记忆回放增强导航。利用视觉语言模型提取三元组，经R-GCN编码投影到双曲空间，采用动态聚类等策略。实验证明其在保留导航能力和泛化性上优于基线。

EndoDDC: Learning Sparse to Dense Reconstruction for Endoscopic Robotic Navigation via Diffusion Depth Completion

EndoDDC: 通过扩散深度补全学习稀疏到密集重建以实现内窥镜机器人导航

Yinheng Lin, Yiming Huang, Beilei Cui, Long Bai, Huxin Gao, Hongliang Ren, Jiewen Lai

机构 * Department of Electronic Engineering, The Chinese University of Hong Kong（电子工程系，香港中文大学） 纠错

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

AI总结 EndoDDC通过扩散模型整合图像、稀疏深度信息和深度梯度特征，提升内窥镜环境下深度重建的准确性和鲁棒性。

Comments Accepted by ICRA 2026

Reinforcement Learning for Follow-the-Leader Robotic Endoscopic Navigation via Synthetic Data

基于合成数据的强化学习用于跟随领导者机器人内窥镜导航

Sicong Gao, Chen Qian, Laurence Xian, Liao Wu, Maurice Pagnucco, Yang Song

机构 * School of Computer Science and Engineering, The University of New South Wales（计算机科学与工程学院，新南威尔士大学） ； School of Mechanical and Manufacturing Engineering, The University of New South Wales（机械与制造工程学院，新南威尔士大学） 纠错

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

AI总结 本文提出了一种基于合成数据的强化学习方法，用于提高内窥镜机器人在狭窄管状环境中的自主导航能力，通过深度学习和几何感知机制提升了导航精度和效率。

RNBF: Real-Time RGB-D Based Neural Barrier Functions for Safe Robotic Navigation

RNBF: 基于实时RGB-D的神经障碍函数用于安全机器人导航

Satyajeet Das, Yifan Xue, Haoming Li, Nadia Figueroa

机构 * University of Southern California（南加州大学） ； University of Pennsylvania（宾夕法尼亚大学） 纠错

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

AI总结 本文提出了一种实时RGB-D神经障碍函数框架，用于在未知环境中实现安全机器人导航，通过在线构建可微的SDFs并处理传感器噪声，提升导航安全性。

LLM-Based Agentic Exploration for Robot Navigation & Manipulation with Skill Orchestration

基于大语言模型的代理探索用于机器人导航与操作的技能编排

Abu Hanif Muhammad Syarubany, Farhan Zaki Rahmani, Trio Widianto

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

AI总结 本文提出基于大语言模型的代理探索系统，用于机器人导航与操作，通过技能编排实现端到端任务执行。

Dynamic Log-Gaussian Process Control Barrier Function for Safe Robotic Navigation in Dynamic Environments

动态对数高斯过程控制屏障函数用于动态环境中的安全机器人导航

Xin Yin, Chenyang Liang, Yanning Guo, Jie Mei

机构 * School of Intelligence Science and Engineering, Harbin Institute of Technology（智能科学与工程学院，哈尔滨工业大学） ； Department of Control Science and Engineering, Harbin Institute of Technology（控制科学与工程学院，哈尔滨工业大学） 纠错

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

AI总结 本文提出动态对数高斯过程控制屏障函数，通过实时构建空间信息丰富且响应障碍物运动的CBF，提升动态环境中机器人导航的安全性和避障性能。

Comments To be presented in the 64th IEEE Conference on Decision and Control (CDC 2025)

Safe Navigation in Unmapped Environments for Robotic Systems with Input Constraints

Amirsaeid Safari, Jesse B. Hoagg

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

Comments The Preprint was submitted to the 2025 Conference on Decision and Control (CDC). arXiv admin note: substantial text overlap with arXiv:2409.01458

VascularPilot3D: Toward a 3D fully autonomous navigation for endovascular robotics

Jingwei Song, Keke Yang, Han Chen, Jiayi Liu, Yinan Gu, Qianxin Hui, Yanqi Huang, Meng Li, Zheng Zhang, Tuoyu Cao, Maani Ghaffari

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

Human Gaze and Head Rotation during Navigation, Exploration and Object Manipulation in Shared Environments with Robots

Tim Schreiter, Andrey Rudenko, Martin Magnusson, Achim J. Lilienthal

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

Comments This is the final version of the accepted version of the manuscript that will be published in the 2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN). Copyright 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses

Journal ref 2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN)

Teledrive: An Embodied AI based Telepresence System

Snehasis Banerjee, Sayan Paul, Ruddradev Roychoudhury, Abhijan Bhattacharya, Chayan Sarkar, Ashis Sau, Pradip Pramanick, Brojeshwar Bhowmick

专题命中 具身导航 ：embodied AI(title,abstract)；robotic(abstract,comments)；navigation(abstract)；分类 cs.RO

Comments Accepted in Journal of Intelligent Robotic System

Journal ref Journal of Intelligent Robotic System 2024

Instance-Specific Image Goal Navigation: Training Embodied Agents to Find Object Instances

Jacob Krantz, Stefan Lee, Jitendra Malik, Dhruv Batra, Devendra Singh Chaplot

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

3D Lidar Reconstruction with Probabilistic Depth Completion for Robotic Navigation

Yifu Tao, Marija Popović, Yiduo Wang, Sundara Tejaswi Digumarti, Nived Chebrolu, Maurice Fallon

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

Comments Accepted at IROS 2022; Video at https://www.youtube.com/watch?v=db3HetMq5h4

Hierarchical Cross-Modal Agent for Robotics Vision-and-Language Navigation

Muhammad Zubair Irshad, Chih-Yao Ma, Zsolt Kira

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

Comments Accepted to ICRA 2021; Code and Dataset are available at https://github.com/GT-RIPL/robo-vln

Learning Partially Structured Environmental Dynamics for Marine Robotic Navigation

Chen Huang, Kai Yin, Lantao Liu

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

Hierarchical Bayesian Data Fusion for Robotic Platform Navigation

Andres F. Echeverri, Henry Medeiros, Ryan Walsh, Yevgeniy Reznichenko, Richard Povinelli

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

Comments 8 pages, 9 figures

Shape and Color Object Tracking for Real-Time Robotic Navigation

Haythem Ghazouani

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

Comments in French

One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay

Jake Bruce, Niko Suenderhauf, Piotr Mirowski, Raia Hadsell, Michael Milford

专题命中 具身导航 ：navigation(title,journal_ref)；robotics(abstract)；world model(abstract)；robot learning(comments,journal_ref)

Comments NIPS Workshop on Acting and Interacting in the Real World: Challenges in Robot Learning

Journal ref Bruce, Jake, et al. "One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay." Proceedings of the NIPS Workshop on Acting and Interacting in the Real World: Challenges in Robot Learning. 2017

Flow-aware Optimal Navigation in Unsteady Flows through Reinforcement Learning

通过强化学习在非定常流中进行流量感知最优导航

Andrea Maria Braghin, Nicolò Botteghi, Matteo Tomasetto, Andrea Manzoni, Gabriele Cazzulani

机构 * Politecnico di Milano（米兰理工大学） ； MOX（数学优化与工程计算实验室） 纠错

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

AI总结 研究在非定常流中自主机器人导航问题，用TD3算法训练智能体在双涡旋流中到达目标。评估五种生物启发观测策略及全局流参数影响，发现速度感知与涡度传感器效用有权衡，明确参数会降性能，为机器人导航从模拟到现实提供见解。

Rectified Schrödinger Bridge Matching for Few-Step Visual Navigation

整流薛定谔桥匹配用于少步视觉导航

Wuyang Luan, Junhui Li, Weiguang Zhao, Wenjian Zhang, Tieru Wu, Rui Ma

机构 * School of Artificial Intelligence, Jilin University（吉林大学人工智能学院） ； College of Computer Science, Chongqing University（重庆大学计算机学院） ； Department of Computer Science, University of Liverpool（利物浦大学计算机科学系） ； Changchun GenY Technology Co., Ltd.（长春GenY科技有限公司） 纠错

专题命中 具身导航 ：navigation(title,abstract)；embodied AI(abstract)；robotic(abstract)；分类 cs.RO、cs.AI

AI总结 提出整流薛定谔桥匹配（RSBM）框架，利用速度场结构不变性和线性方差减少，在仅3步积分中实现高保真生成策略，满足具身AI低延迟需求。

Comments 18 pages, 7 figures, 10 tables. Code available at https://github.com/WuyangLuan/RSBM

OSMa-Bench++: Toward Open-Ended Benchmarking of Semantic Mapping for Manipulation with Prompt-Generated Synthetic Scenes

OSMa-Bench++：面向操作任务的语义映射开放基准测试，使用提示生成的合成场景

Regina Kurkova, Maxim Popov, Sergey Kolyubin

机构 * Biomechatronics and Energy-Efficient Robotics (BE2R) Lab, ITMO University（生物机电学与节能机器人实验室，ITMO大学） 纠错

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

AI总结 本文扩展OSMa-Bench，通过提示生成合成室内场景实现可控基准测试，并提出一种基于提示的VQA类别，用于语义映射方法在杂乱、小物体、部分遮挡和光照变化等条件下的压力测试。

Comments Code: https://github.com/be2rlab/OSMa-Bench-v2