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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Chen, S., Cheng, C., Li, F., Wang, T., & Zhao, W. (2026). Learning Language-Conditioned Traversability Representations for Adaptive Visual Navigation. https://omanscience.com/en/articles/learning-language-conditioned-traversability-representations-for-adaptive-visual-navigation
MLA 9
Chen, Senda, et al. "Learning Language-Conditioned Traversability Representations for Adaptive Visual Navigation." https://omanscience.com/en/articles/learning-language-conditioned-traversability-representations-for-adaptive-visual-navigation.
Chicago (author–date)
Chen, Senda, Changxu Cheng, Fangdi Li, Tao Wang, and Wuyue Zhao. 2026. "Learning Language-Conditioned Traversability Representations for Adaptive Visual Navigation." https://omanscience.com/en/articles/learning-language-conditioned-traversability-representations-for-adaptive-visual-navigation.
Harvard
Chen, S., Cheng, C., Li, F., Wang, T. and Zhao, W. (2026) 'Learning Language-Conditioned Traversability Representations for Adaptive Visual Navigation', Available at: https://omanscience.com/en/articles/learning-language-conditioned-traversability-representations-for-adaptive-visual-navigation.
Vancouver
Chen S, Cheng C, Li F, Wang T, Zhao W. Learning Language-Conditioned Traversability Representations for Adaptive Visual Navigation. https://omanscience.com/en/articles/learning-language-conditioned-traversability-representations-for-adaptive-visual-navigation
IEEE
S. Chen, C. Cheng, F. Li, T. Wang, and W. Zhao, "Learning Language-Conditioned Traversability Representations for Adaptive Visual Navigation," https://omanscience.com/en/articles/learning-language-conditioned-traversability-representations-for-adaptive-visual-navigation.