外观
论文arXiv 2610.1162220 天前
学习语言条件化可通行性表征用于自适应视觉导航
原文链接：Learning Language-Conditioned Traversability Representations for Adaptive Visual Navigation（arXiv 2610.11622 · 发布日期：2026-10-08）
Learning Language-Conditioned Traversability Representations for Adaptive Visual Navigation
LaTraNav学习语言条件化可通行性表征，结合慢速VLM与快速规划器，在多来源数据集上验证自适应视觉导航。
核心要点
- 可通行性随机器人能力和用户偏好变化，传统代价地图或分割掩码依赖手工规则与调参。
- 框架采用异步架构，用慢速视觉语言模型生成可通行性与目标潜表征，并由快速flow-matching规划器条件化规划。
- 通过基于仿真的数据生成管线产生带语言、可通行性图、目标位置和多样轨迹的观测，并用图像翻译增强真实感。
- 多来源数据集评估显示其支持语言引导分割、目标定位和像素空间路径规划，潜表征优于显式掩码，路径更新率提升6.05倍。
验证范围与局限：验证范围为多来源数据集上的可通行性分割、目标定位和像素空间路径规划，摘要未提及真机实验。
英文摘要 (Abstract)
Traversability is essential for visual navigation but varies with robot capabilities and user preferences. Conventional pipelines often rely on explicit costmaps or segmentation masks with predefined criteria, requiring hand-crafted rules and careful tuning. Moreover, viewpoint-dependent segmentation masks complicate asynchronous planning under perception latency. We present LaTraNav, a framework that learns language-conditioned traversability representations for adaptive visual navigation. Its asynchronous architecture combines a slow vision-language model that produces latent representations of traversability and navigation goals, with a fast flow-matching planner conditioned on these representations. To train the system, we develop a simulation-based data generation pipeline with controllable trajectories, producing observations paired with language instructions, traversability maps, goal locations, and diverse trajectories. Photorealistic image translation further enhances visual realism. Evaluations on datasets from multiple sources demonstrate effective language-guided traversability segmentation and goal localization by the slow VLM, alongside adaptive pixel-space path planning by the fast planner. Latent conditioning improves planning performance over explicit segmentation masks, while asynchronous scheduling increases the path-update rate by $6.05\times$ at the same semantic-update rate.
作者：Senda Chen, Changxu Cheng, Fangdi Li, Tao Wang, Wuyue Zhao
来源
本页事实对应的公开页面，以原文为准。