GARL: Genetic Algorithm-Augmented Reinforcement Learning to Detect Violations in Marker-Based Autonomous Landing Systems

TL;DR

GARL combines genetic algorithms and reinforcement learning to efficiently generate diverse failure scenarios for autonomous UAV landing systems, enhancing safety testing beyond traditional static or extensive online methods.

Contribution

The paper introduces GARL, a novel framework that integrates GA and RL to generate realistic landing failures efficiently, improving testing diversity and effectiveness.

Findings

Outperforms existing methods by up to 18.35% in violation rate.

Achieves 58% improvement in diversity metric.

Validates violations through real-world UAV tests.

Abstract

Automated Uncrewed Aerial Vehicle (UAV) landing is crucial for autonomous UAV services such as monitoring, surveying, and package delivery. It involves detecting landing targets, perceiving obstacles, planning collision-free paths, and controlling UAV movements for safe landing. Failures can lead to significant losses, necessitating rigorous simulation-based testing for safety. Traditional offline testing methods, limited to static environments and predefined trajectories, may miss violation cases caused by dynamic objects like people and animals. Conversely, online testing methods require extensive training time, which is impractical with limited budgets. To address these issues, we introduce GARL, a framework combining a genetic algorithm (GA) and reinforcement learning (RL) for efficient generation of diverse and real landing system failures within a practical budget. GARL employs GA for exploring various environment setups offline, reducing the complexity of RL's online testing in simulating challenging landing scenarios. Our approach outperforms existing methods by up to 18.35% in violation rate and 58% in diversity metric. We validate most discovered violation types with real-world UAV tests, pioneering the integration of offline and online testing strategies for autonomous systems. This method opens new research directions for online testing, with our code and supplementary material available at https://github.com/lfeng0722/drone_testing/.