Safe and Economical UAV Trajectory Planning in Low-Altitude Airspace: A Hybrid DRL-LLM Approach with Compliance Awareness

TL;DR

This paper introduces a hybrid DRL-LLM framework for UAV trajectory planning that ensures safety, compliance, and cost-effectiveness in complex urban low-altitude environments, outperforming existing methods.

Contribution

It presents a novel combination of deep reinforcement learning and large language models to improve UAV trajectory planning under urban airspace constraints.

Findings

Significant improvement in collision avoidance and safety metrics.

Enhanced regulatory compliance and energy efficiency.

Higher success rates in landing and data collection.

Abstract

The rapid growth of the low-altitude economy has driven the widespread adoption of unmanned aerial vehicles (UAVs). This growing deployment presents new challenges for UAV trajectory planning in complex urban environments. However, existing studies often overlook key factors, such as urban airspace constraints and economic efficiency, which are essential in low-altitude economy contexts. Deep reinforcement learning (DRL) is regarded as a promising solution to these issues, while its practical adoption remains limited by low learning efficiency. To overcome this limitation, we propose a novel UAV trajectory planning framework that combines DRL with large language model (LLM) reasoning to enable safe, compliant, and economically viable path planning. Experimental results demonstrate that our method significantly outperforms existing baselines across multiple metrics, including data collection rate, collision avoidance, successful landing, regulatory compliance, and energy efficiency. These results validate the effectiveness of our approach in addressing UAV trajectory planning key challenges under constraints of the low-altitude economy networking.