HTNav: A Hybrid Navigation Framework with Tiered Structure for Urban Aerial Vision-and-Language Navigation
2026-04-10 • Robotics
RoboticsArtificial Intelligence
AI summaryⓘ
The authors created HTNav, a system that helps drones or robots navigate complex city environments better by combining two learning methods: imitation learning and reinforcement learning. Their approach trains the system in stages to keep navigation stable while exploring new areas effectively. They also use a special map-learning part to help the system understand how spaces connect, which improves planning routes and actions. Tests show HTNav works better than earlier methods in different city scenes and tasks.
Vision-and-Language Navigation (VLN)Imitation Learning (IL)Reinforcement Learning (RL)Hybrid IL-RL frameworkPath planningSpatial continuityMap representation learningCityNav benchmarkNavigation precisionUrban environments
Authors
Chengjie Fan, Cong Pan, Zijian Liu, Ningzhong Liu, Jie Qin
Abstract
Inspired by the general Vision-and-Language Navigation (VLN) task, aerial VLN has attracted widespread attention, owing to its significant practical value in applications such as logistics delivery and urban inspection. However, existing methods face several challenges in complex urban environments, including insufficient generalization to unseen scenes, suboptimal performance in long-range path planning, and inadequate understanding of spatial continuity. To address these challenges, we propose HTNav, a new collaborative navigation framework that integrates Imitation Learning (IL) and Reinforcement Learning (RL) within a hybrid IL-RL framework. This framework adopts a staged training mechanism to ensure the stability of the basic navigation strategy while enhancing its environmental exploration capability. By integrating a tiered decision-making mechanism, it achieves collaborative interaction between macro-level path planning and fine-grained action control. Furthermore, a map representation learning module is introduced to deepen its understanding of spatial continuity in open domains. On the CityNav benchmark, our method achieves state-of-the-art performance across all scene levels and task difficulties. Experimental results demonstrate that this framework significantly improves navigation precision and robustness in complex urban environments.