首个面向真实场景兴趣点导航的基准，解决最后百米定位难题。
POINav: Benchmarking and Enhancing Final-Meters Arrival in Real-World Vision-Language Navigation
- 构建基于3D高斯泼溅的真实商业区地图，支持闭环评估。
- 覆盖126,398平方米、163个兴趣点，含可通行性标注与参考轨迹。
- 提出脑-行动框架，结合实景标识对齐提升导航精度。
现实世界导航本质上依赖于兴趣点（POI），但精准抵达目标点仍是关键的“最后百米”挑战。现有视觉语言导航（VLN）基准在POI目标导航中常因场景生成导致粒度粗糙或严重仿真到现实差距。为此，我们提出首个面向闭环评估的真实世界POI目标导航基准POINav-Bench，其基于3D高斯泼溅（3DGS）重建11个真实商业区域，总面积达126,398 $m^{2}$，涵盖163个不同POI。该基准提供可通行性标注和参考轨迹，支持在真实、富含兴趣点的环境中高保真评估导航智能体。在此基础上，我们提出POINav脑-行动框架：由脑模块执行基于POI的推理，引导动作模块预测可用于真实执行的连续航点。此外，我们还构建了包含70,000组实景标识-入口配对的POINav-Dataset。实验表明，该框架为优化真实世界POI目标导航提供了可行路径。
原文摘要 · Abstract (English)
Real-world navigation is fundamentally driven by Points of Interest (POIs), yet reaching a precise POI remains a critical "final-meters" challenge. Existing Vision-Language Navigation (VLN) benchmarks of POI-goal navigation often suffer from coarse granularity or significant sim-to-real gaps due to generated scene. To bridge this gap, we present POINav-Bench, the first benchmark designed for closed-loop evaluation of real-world POI-goal navigation. It comprises 11 commercial areas reconstructed from real-world captures using 3D Gaussian Splatting (3DGS), covering 126,398 $m^{2}$ in total and spanning 163 distinct POIs. With traversability-aware annotations and reference trajectories, POINav-Bench enables high-fidelity evaluation of navigation agents in realistic, POI-rich real-world environments. Building on this, we propose the POINav Brain-Action Framework where a Brain module performs POI-grounded reasoning to guide an Action module in predicting continuous waypoints for real-world execution. We further curate the POINav-Dataset, containing 70K real-world signage-entrance pairs. Experiments show that our framework provides a viable path toward refining real-world POI-goal navigation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。