机器人 / 具身智能

A 64mW DNN-based Visual Navigation Engine for Autonomous Nano-Drones

Daniele Palossi, Antonio Loquercio, Francesco Conti, Eric Flamand, Davide Scaramuzza, Luca Benini

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

Comments 15 pages, 13 figures, 5 tables, 2 listings, accepted for publication in the IEEE Internet of Things Journal (IEEE IOTJ)

Exploration of Self-Propelling Droplets Using a Curiosity Driven Robotic Assistant

Jonathan Grizou, Laurie J. Points, Abhishek Sharma, Leroy Cronin

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

A Critical Investigation of Deep Reinforcement Learning for Navigation

Vikas Dhiman, Shurjo Banerjee, Brent Griffin, Jeffrey M Siskind, Jason J Corso

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

IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments

Girish Varma, Anbumani Subramanian, Anoop Namboodiri, Manmohan Chandraker, C V Jawahar

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

Comments WACV'19

Path planning for Robotic Mobile Fulfillment Systems

Marius Merschformann, Lin Xie, Daniel Erdmann

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

On the Complexity of Exploration in Goal-Driven Navigation

Maruan Al-Shedivat, Lisa Lee, Ruslan Salakhutdinov, Eric Xing

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

Comments Relational Representation Learning Workshop (NIPS 2018)

Shared Multi-Task Imitation Learning for Indoor Self-Navigation

Junhong Xu, Qiwei Liu, Hanqing Guo, Aaron Kageza, Saeed AlQarni, Shaoen Wu

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

Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments

Xi Chen, Ali Ghadirzadeh, John Folkesson, Patric Jensfelt

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

Comments Submitted to IROS 2018

Offline and Online calibration of Mobile Robot and SLAM Device for Navigation

Ryoichi Ishikawa, Takeshi Oishi, Katsushi Ikeuchi

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

Autonomous development and learning in artificial intelligence and robotics: Scaling up deep learning to human--like learning

Pierre-Yves Oudeyer

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

Journal ref Behavioral and Brain Sciences, Cambridge University Press (CUP), 2017, 40

Smoothness-based Edge Detection using Low-SNR Camera for Robot Navigation

Vu Hoang Minh, Tajwar Abrar Aleef, Usama Pervaiz, Yeman Brhane Hagos, Saed Khawaldeh

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

A Real-Time Deep Learning Pedestrian Detector for Robot Navigation

David Ribeiro, Andre Mateus, Pedro Miraldo, Jacinto C. Nascimento

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

Journal ref IEEE Int'l Conf. Autonomous Robot Systems and Competitions (ICARSC), 2017

Integration of navigation and action selection functionalities in a computational model of cortico-basal ganglia-thalamo-cortical loops

Benoît Girard, David Filliat, Jean-Arcady Meyer, Alain Berthoz, Agnès Guillot

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

Journal ref Adaptive Behavior 13 (2005) 115-130

Autonomous navigation for low-altitude UAVs in urban areas

Thomas Castelli, Aidean Sharghi, Don Harper, Alain Tremeau, Mubarak Shah

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

Optimizing Gaze Direction in a Visual Navigation Task

Tuomas Välimäki, Risto Ritala

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

Simplified vision based automatic navigation for wheat harvesting in low income economies

Muhammad Zubair Ahmad, Ayyaz Akhtar, Abdul Qadeer Khan, Amir A. Khan

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

Autonomous Navigation by Robust Scan Matching Technique

Debajyoti Banerji, Ranjit Ray, Jhankar Basu, Indrajit Basak

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

Comments 7 pages, 9 figures

Journal ref INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711), VOL.2 NO.10 OCTOBER 2012

Robotic Mapping with Polygonal Random Fields

Mark Paskin, Sebastian Thrun

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

Comments Appears in Proceedings of the Twenty-First Conference on Uncertainty in Artificial Intelligence (UAI2005)

Vision-Based Navigation III: Pose and Motion from Omnidirectional Optical Flow and a Digital Terrain Map

Ronen Lerner, Oleg Kupervasser, Ehud Rivlin

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

Comments 6 pages, 9 figures

Journal ref Proceedings of the 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems October 9 - 15, 2006, Beijing, China

Learning Geometrically-Constrained Hidden Markov Models for Robot Navigation: Bridging the Topological-Geometrical Gap

L. P. Kaelbling, H. Shatkay

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

Journal ref Journal Of Artificial Intelligence Research, Volume 16, pages 167-207, 2002

DevGRU: Depth-guided Visual Navigation using a Collision-aware Recurrent Model

DevGRU：基于碰撞感知循环模型的深度引导视觉导航

Kyung Min Han, Eunsom Kim, Young J. Kim

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

AI总结 针对现有视觉导航模型易在复杂室内环境碰撞的问题，提出DevGRU导航系统，结合动作与碰撞预测器提升导航性能，在9种场景实验中优于多种基线模型，且模型规模小、推理速度快

Comments Accepted for publication in IEEE Robotics and Automation Letters (RA-L), 2026

Graph-MambaNav: Spatial-Temporal Graph Mamba Leveraging Object-Relation Knowledge for Object-Goal Navigation

Graph-MambaNav：利用对象关系知识的时空图Mamba用于目标对象导航

Leyuan Sun, Genxin Chen, Linwei Ye, Yan Zhang, Xi Kan, Yanfei Sun

机构 * School of Internet of Things Engineering, Wuxi University（无锡大学物联网工程学院） ； School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications（南京邮电大学通信与信息工程学院） 纠错

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

AI总结 本研究提出Graph-MambaNav，一种结合LLM常识对象关系的目标感知时空图编码框架，通过节点排序与Mamba建模实现高效导航，在仿真环境表现优异且泛化性好，经真实机器人部署验证有效。

Comments Accepted by IEEE Robotics and Automation Letters (IEEE RA-L), will transfer to 2027 IEEE International Conference on Robotics & Automation (ICRA)

MPPI Planning with Gaussian-Based Human Cost Function for Social Navigation

基于高斯人类代价函数的MPPI规划用于社交导航

Chinmay Mundane

机构 * VJTI（维杰拉吉·鲁勒学院（VJTI）） 纠错

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

AI总结 该研究针对普通MPPI规划低估动态场景风险的问题，提出PGIF方法，结合高斯排斥场实现0%碰撞率，同时保持实时规划性能，适用于社交导航。

Comments Will appear in Springer's Proceedings in Advanced Robotics series

Robust Scene Transfer for PointGoal Navigation via Privileged Sensor Guided Contrastive Learning

基于特权传感器引导对比学习的点目标导航鲁棒场景迁移

Amirhossein Zhalehmehrabi, Tiziano Tezze, Alberto Castelini, Alessandro Farinelli

机构 * University of Padua（帕多瓦大学） ； ETH Zurich（苏黎世联邦理工学院） 纠错

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

AI总结 提出一种传感器引导的自适应对比学习框架，利用特权LiDAR传感器在训练时引导视觉编码器学习导航相关结构，并通过解耦表征学习与策略优化以及跨阶段域不匹配来提升策略级场景迁移能力。

Comments 8 pages, Accepted to IEEE Robotics and Automation Letters (RA-L)

FlowPilot: Real-Time World-Action Modeling for Agile UAV Navigation

FlowPilot：面向敏捷无人机导航的实时世界-动作建模

Runqing Wang, Ding Yu, Pengyuan Min, Xinhong Zhang, Wei Xiao, Yu Hu, Jie Chen, Fu Zhang, Gang Wang

机构 * Beijing Institute of Technology（北京理工大学） ； Zhongguancun Academy（中关村学院） ； Shanghai Jiao Tong University（上海交通大学） ； The University of Hong Kong（香港大学） 纠错

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

AI总结 FlowPilot是一种基于流匹配的紧凑世界-动作模型，采用双流混合Transformer，在三级深度金字塔数据上训练，可实现敏捷无人机实时导航，性能优于基线，能在杂乱环境中以5.5m/s速度运行。

Comments 8 pages, 9 figures, 2 tables, submitted to IEEE Robotics and Automation Letters (RA-L)

Learning When to Jump for Off-road Navigation

在越野导航中学习何时跳跃

Zhipeng Zhao, Taimeng Fu, Shaoshu Su, Qiwei Du, Ehsan Tarkesh Esfahani, Karthik Dantu, Souma Chowdhury, Chen Wang

机构 * University at Buffalo（布法罗大学） 纠错

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

AI总结 本文提出Motion-aware Traversability方法，通过建模实际机器人运动动态，提升越野导航的实时性和安全性，减少75%的路径绕行。

Journal ref Robotics: Science and Systems (RSS), 2026

AutoPath: Learning Transferable Goal-Conditioned Stochastic Path Prior for Safe Navigation Without Human Demonstrations

AutoPath：学习可转移的目标条件随机路径先验以实现无人类示范的安全导航

Ziyang Zhang, Boyang Zhou, Zesong Yang, Haocheng Peng, Zeming Gai, Xiao Liang, Yujun Shen, Danping Zou, Ruizhen Hu, Hujun Bao, Zhaopeng Cui

机构 * Zhejiang University（浙江大学） ； Harbin Institute of Technology（哈尔滨工业大学） ； Ant Group（蚂蚁集团） ； Shanghai Jiao Tong University（上海交通大学） ； Shenzhen University（深圳大学） 纠错

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

AI总结 研究在复杂环境下的安全导航问题，提出学习可转移目标条件随机路径先验的方法，引入规范状态表示和结构化先验学习框架，实验证明该方法成功率高、效率有竞争力且可跨平台转移。

Comments Accepted by IEEE Robotics and Automation Letters (RA-L). 8 pages, 4 figures

TRISTAR: Triple-Signal Stair Recognition and Vision-Only Indoor Navigation for Search-and-Rescue Micro-UAVs

TRISTAR：用于搜索救援微型无人机的三重信号楼梯识别与仅视觉室内导航

Octavian Gîngu, Stelian Spînu

机构 * Military Technical Academy（军事技术学院） 纠错

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

AI总结 研究为低成本无人机提出仅基于单目视觉的室内导航框架。结合深度估计、传统计算机视觉和轻量级深度学习模型。核心方法是TRISTAR三重传感器融合，贡献是实现可靠室内探索与楼梯穿越，无需特殊测距硬件。

Comments 10 pages, 7 figures. Project repository available at: https://github.com/tavigingu/HawkOps-Indoor-Drone-Navigation-and-TRISTAR-Stair-Climbing

Towards Data-Driven Metrics for Social Robot Navigation Benchmarking

迈向用于社交机器人导航基准测试的数据驱动指标

Pilar Bachiller-Burgos, Ulysses Bernardet, Luis V. Calderita, Pranup Chhetri, Anthony Francis, Noriaki Hirose, Noé Pérez, Dhruv Shah, Phani T. Singamaneni, Xuesu Xiao, Luis J. Manso

机构 * Aston University（阿斯顿大学） ； Logical Robotics（逻辑机器人公司） ； University of California Berkeley（加州大学伯克利分校） ； TOYOTA Motor North America（丰田北美公司） ； Princeton University（普林斯顿大学） ； LAAS-CNRS（LAAS-CNRS研究所） ； George Mason University（乔治·梅森大学） 纠错

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

AI总结 致力于开发数据驱动的社交机器人导航指标以促进地面机器人基准测试和策略优化，介绍方法动机、数据集格式等，给出首个全面的学习社交机器人导航指标及相关结果。

Comments This work was presented at the 18th International Conference on Social Robotics (ICSR'2026)

Robust Extended Kalman Filter for Land Navigation Using Massive Array of MEMS IMUs

基于大规模MEMS IMU阵列的陆地导航鲁棒扩展卡尔曼滤波

Omer Hanani, Alon Kipnis

机构 * School of Computer Science, Reichman University（里奇曼大学计算机科学学院） 纠错

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

AI总结 提出一种鲁棒扩展卡尔曼滤波架构，通过动态百分位门控和实时偏置跟踪的预滤波框架，有效融合数百个低成本MEMS惯性传感器，抑制异常读数并补偿漂移，显著提升方位精度并降低漂移累积。

Comments Index Terms Dead reckoning Extended Kalman Filter GNSS IMU array Land navigation