Vision-Language Navigation

Also known as VLN

Overview

Vision-Language Navigation (VLN) asks embodied agents—such as mobile robots and drones—to follow language instructions by interpreting what they see and choosing actions over time. Approaches range from end-to-end vision-language policies to hierarchical systems that combine large models with maps, scene graphs, spatial memory, geometric planners, and world models; imitation learning and reinforcement learning are common training strategies. Methods are tested on benchmarks such as R2R, RxR, REVERIE, VLN-CE, and HM3D, with growing attention to object goals, outdoor and aerial settings, and real-robot deployment. A central challenge is turning correct language and scene understanding into safe, efficient behavior over long routes, where localization drift, changing scenes, limited compute, and the gap between simulation and reality can cause failures.

Latest papers

CardsList

334 papers28 papers in the last four weeks, down 48% on the four weeks before. 0.2% of all new papers.

  1. ATLAS Navigator: Active Task-driven LAnguage-embedded Gaussian Splatting

    Feb 27, 2025Dexter Ong, Yuezhan Tao, Varun Murali +33D Gaussian SplattingLanguage-Embedded 3DGS

  2. VL-Nav: Neuro-Symbolic Reasoning-based Vision-Language Navigation

    Feb 2, 2025Yi Du, Taimeng Fu, Zhipeng Zhao +6Robot NavigationVision-Language Navigation

  3. Open-Vocabulary Object-Goal Navigation by Generalizing Semantic Mapping with Dense CLIP

    Jul 12, 2024Meng Wei, Chenyang Wan, Tai Wang +6Embodied NavigationVision-Language Navigation