HTNav: A Hybrid Navigation Framework with Tiered Structure for Urban Aerial Vision-and-Language Navigation

2026-04-10

AI Summary

This work addresses the limitations of weak generalization, poor long-horizon planning, and insufficient spatial continuity understanding in urban vision-and-language navigation. To overcome these challenges, the authors propose HTNav, a novel hierarchical framework that synergistically integrates imitation learning and reinforcement learning within a collaborative decision-making architecture. HTNav employs a staged training strategy to jointly optimize high-level path planning and fine-grained action control, while incorporating a map representation learning module to enhance spatial comprehension of unseen urban environments. Evaluated on the CityNav benchmark, HTNav achieves state-of-the-art performance across all scene scales and task difficulties, significantly improving navigation accuracy and robustness in complex urban settings.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Vision-and-Language Navigation
• urban aerial navigation
• spatial continuity
• generalization
• long-range path planning

Innovation

• Hybrid IL-RL Framework
• Tiered Decision-Making
• Map Representation Learning
• Aerial Vision-and-Language Navigation
• Staged Training Mechanism