# HaltNav: Reactive Visual Halting over Lightweight Topological Priors for Robust Vision-Language Navigation Source: [HaltNav: Reactive Visual Halting over Lightweight Topological Priors for Robust Vision-Language Navigation]() Collection index: [llms.txt]() Data updated: 2026-03-21T05:00:04.296Z Authors: Zihui Yu, Pingcong Li, Bichi Zhang, S\\"oren Schwertfeger Published: 2026-03-13T06:22:35.000Z ## Abstract Vision-and-Language Navigation (VLN) is shifting from rigid, step-by-step instruction following toward open-vocabulary, goal-oriented autonomy. Achieving this transition without exhaustive routing prompts requires agents to leverage structural priors. While prior work often assumes computationally heavy 2D/3D metric maps, we instead exploit a lightweight, text-based osmAG (OpenStreetMap Area Graph), a floorplan-level topological representation that is easy to obtain and maintain. However, global planning over a prior map alone is brittle in real-world deployments, where local connectivity can change (e.g., closed doors or crowded passages), leading to execution-time failures. To address this gap, we propose a hierarchical navigation framework HaltNav that couples the robust global planning of osmAG with the local exploration and instruction-grounding capability of VLN. Our approach features an MLLM-based brain module, which is capable of high-level task grounding and obstruction awareness. Conditioned on osmAG, the brain converts the global route into a sequence of localized execution snippets, providing the VLN executor with prior-grounded, goal-centric sub-instructions. Meanwhile, it detects local anomalies via a mechanism we term Reactive Visual Halting (RVH), which interrupts the local control loop, updates osmAG by invalidating the corresponding topology, and triggers replanning to orchestrate a viable detour. To train this halting capability efficiently, we introduce a data synthesis pipeline that leverages generative models to inject realistic obstacles into otherwise navigable scenes, substantially enriching hard negative samples. Extensive experiments demonstrate that our hierarchical framework outperforms several baseline methods without tedious language instructions, and significantly improves robustness for long-horizon vision-language navigation under environmental changes. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Vision-and-Language Navigation on Fetch Robot Real-World (Standard (B))](): Vision-and-Language Navigation; Fetch Robot Real-World (Standard (B)); Success Rate (SR): 73.33. - [Vision-and-Language Navigation on Fetch Robot Real-World Obstacle-Injected (O)](): Vision-and-Language Navigation; Fetch Robot Real-World Obstacle-Injected (O); SR (%): 56.66. - [Vision-and-Language Navigation on HM3D Simulation](): Vision-and-Language Navigation; HM3D Simulation; SR (B): 79.38. ## Original sources and implementation [Original paper]() [PDF]()