Image-Goal Navigation

Ask about this topic

Overview

Image-goal navigation studies how an embodied agent can reach a place or object shown in a goal image, often without coordinates or a prebuilt map. Methods range from goal-conditioned reinforcement-learning policies and topological mapping to vision-language planning and world models that predict future observations or action sequences; geometric localization and local planners help execute safely. Systems are evaluated in simulated indoor environments such as Habitat and on physical ground and aerial robots, with measures including success rate, path efficiency, localization error, and collisions. A central challenge is balancing robust long-horizon navigation and precise arrival with real-time inference, uncertainty handling, and safe transfer from simulation to the real world.

Latest papers

CardsList

17 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

  1. Omni-IGN: Onboard Image-Goal Navigation for Drones with Omnidirectional Vision

    Oct 27, 2026Zichen Yan, Rui Huang, Shenao Wang +3UAV NavigationImage-Goal Navigation

    Department of Electrical and Computer Engineering, National University of Singapore, Singapore.

  2. GS-PRM: Gaussian Visual Roadmap for Image-Goal Navigation

    Oct 14, 2026Ashraf Siddique, Kyung Min Han, Young J. KimRobot NavigationImage-Goal Navigation

  3. G2^2WAM: World Action Models for Efficient and Geometry Grounded Image-Goal Navigation

    Oct 12, 2026Ke Gui, Chenghao Shi, Ziyue Wang +3Scene Coordinate RegressionImage-Goal Navigation

    College of Intelligence Science and Technology, National University of Defense Technology, China · National Key Laboratory of Equipment State Sensing and Smart Support, National University of Defense Technology, China · School of Future Technology, National University of Defense Technology, China

  4. WAVE-Go: World-Model Navigation with Adaptive Execution for Wheel-Legged Robots

    Sep 16, 2026Mingyi Li, Ji Li, Zhihao Ouyang +2Visual NavigationWorld Models for Robotics

    Beijing Institute of Technology · The University of Hong Kong · GAC R&D Center +2

  5. EgoNav: Bridging Learned Waypoints and Geometry-Aware Local Control for Robust Indoor Navigation

    Aug 26, 2026Jing Wang, Shiqi Zhao, Hairong Qu +1Robot NavigationIndoor Robot Navigation

    City University of Hong Kong, Hong Kong, China

  6. Latent World Models with Monotone Planning Costs for Image-Goal Navigation

    Aug 10, 2026Amirhosein Chahe, Siwei Cai, Lifeng ZhouVisual NavigationWorld Model Learning

    Drexel University

  7. Unordered Landmark Visual Navigation

    Aug 7, 2026Hao Ren, Junzhe Zhu, Yihan Li +8Visual NavigationRobot Navigation

    Sun Yat-sen University, Guangzhou, China · Insta360 Research, Shenzhen, China

  8. Uncertainty-Aware World Model for Aerial Image-Goal Navigation

    Aug 6, 2026Deyi Zhu, Haoyu Fan, Yinan Zhu +4Uncertainty QuantificationWorld Models for Robotics

    Tsinghua Shenzhen International Graduate School, Tsinghua University

  9. UniNav: A Unified World-Action Diffusion Model for Visual Navigation

    Aug 4, 2026Changqing Zhou, Yueru Luo, Zeyu Jiang +1Visual NavigationTrajectory Generation

    1The Hong Kong University of Science and Technology (Guangzhou) · 2The Chinese University of Hong Kong, Shenzhen

  10. RASR: Range-Aware Scale Recovery for Metric UAV Navigation

    Jul 10, 2026Hongtao Liang, Xinyu Shao, Chenxu Wang +5Visual NavigationMetric Depth Estimation

    College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, China · Shenzhen International Graduate School, Tsinghua University, China · 3Noah Ark Lab, Huawei, China +3

  11. RoamFlow: Reinforcement-Aligned One-Step Action MeanFlow Policy for Image-Goal Navigation

    Jun 29, 2026Zixuan Zhang, Yuqi Chen, Junjie Gao +4Visual NavigationRobot Navigation

    Nanyang Technological University, Singapore

  12. Flying to Image-Specified Objects: 3D Quadrotor Navigation via Cross-Graph Memory and Viewpoint Planning

    Jun 29, 2026Junjie Gao, Yuqi Chen, Yongzhou Pan +3Visual NavigationNext-Best-View Planning

    Nanyang Technological University, Singapore.

  13. NavWAM: A Navigation World Action Model for Goal-Conditioned Visual Navigation

    Jun 11, 2026Daichi Azuma, Taiki Miyanishi, Koya Sakamoto +6World Models for RoboticsRobot Navigation

    The University of Tokyo · National Institute of Informatics · AIRoA +1

  14. Think before Go: Hierarchical Reasoning for Image-goal Navigation

    Apr 19, 2026Pengna Li, Kangyi Wu, Shaoqing Xu +5Visual NavigationRobot Policy Learning

    National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, National Engineering Research Center for Visual Information and Applications, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University · Xiaomi EV · University of Macau +1

  15. AnyImageNav: Any-View Geometry for Precise Last-Meter Image-Goal Navigation

    Apr 7, 2026Yijie Deng, Shuaihang Yuan, Yi FangImage MatchingVisual Robot Navigation

    NYUAD Center for Artificial Intelligence and Robotics (CAIR), Abu Dhabi, UAE · New York University Abu Dhabi, Electrical Engineering, Abu Dhabi 129188, UAE · New York University, Electrical & Computer Engineering Dept., Brooklyn, NY 11201, USA. +1

  16. 120 Minutes and a Laptop: Minimalist Image-goal Navigation via Unsupervised Exploration and Offline RL

    Mar 27, 2026Xiaoming Liu, Borong Zhang, Qingbiao Li +1Robot NavigationImage-Goal Navigation

    Faculty of Science and Technology, University of Macau

  17. MWM: Mobile World Models for Action-Conditioned Consistent Prediction

    Mar 8, 2026Han Yan, Zishang Xiang, Zeyu Zhang +1World Models for RoboticsAction-Conditioned World Models

    School of Computer Science, Peking University