OpenVLN: Open-world Aerial Vision-Language Navigation

TL;DR

OpenVLN introduces a data-efficient framework for aerial vision-language navigation that enhances UAV long-horizon trajectory planning in complex outdoor environments, demonstrating improved success rates in diverse scenarios.

Contribution

The paper presents a novel reinforcement learning-based approach to fine-tune vision-language models for UAV navigation with limited data and introduces a dynamic long-horizon planner for trajectory synthesis.

Findings

Up to 4.34% success rate improvement over baselines

Enhanced long-horizon trajectory planning capabilities

Validated on the TravelUAV benchmark with diverse reward settings

Abstract

Vision-language models (VLMs) have been widely-applied in ground-based vision-language navigation (VLN). However, the vast complexity of outdoor aerial environments compounds data acquisition challenges and imposes long-horizon trajectory planning requirements on Unmanned Aerial Vehicles (UAVs), introducing novel complexities for aerial VLN. To address these challenges, we propose a data-efficient Open-world aerial Vision-Language Navigation (i.e., OpenVLN) framework, which could execute language-guided flight with limited data constraints and enhance long-horizon trajectory planning capabilities in complex aerial environments. Specifically, we reconfigure a reinforcement learning framework to optimize the VLM for UAV navigation tasks, which can efficiently fine-tune VLM by using rule-based policies under limited training data. Concurrently, we introduce a long-horizon planner for trajectory synthesis that dynamically generates precise UAV actions via value-based rewards. To the end, we conduct sufficient navigation experiments on the TravelUAV benchmark with dataset scaling across diverse reward settings. Our method demonstrates consistent performance gains of up to 4.34% in Success Rate, 6.19% in Oracle Success Rate, and 4.07% in Success weighted by Path Length over baseline methods, validating its deployment efficacy for long-horizon UAV navigation in complex aerial environments.