GARL: Genetic Algorithm-Augmented Reinforcement Learning to Detect Violations in Marker-Based Autonomous Landing Systems
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 available at https://anonymous.4open.science/r/drone_testing-5CF0/.
Wed 30 AprDisplayed time zone: Eastern Time (US & Canada) change
11:00 - 12:30 | AutonomyResearch Track at 213 Chair(s): Lionel Briand University of Ottawa, Canada; Lero centre, University of Limerick, Ireland | ||
11:00 15mTalk | A Differential Testing Framework to Identify Critical AV Failures Leveraging Arbitrary Inputs Research Track Trey Woodlief University of Virginia, Carl Hildebrandt University of Virginia, Sebastian Elbaum University of Virginia | ||
11:15 15mTalk | Automating a Complete Software Test Process Using LLMs: An Automotive Case Study Research Track Shuai Wang , Yinan Yu Chalmers University of Technology, Robert Feldt Chalmers | University of Gothenburg, Dhasarathy Parthasarathy Volvo Group Pre-print | ||
11:30 15mTalk | LLM-Agents Driven Automated Simulation Testing and Analysis of small Uncrewed Aerial Systems Research Track Venkata Sai Aswath Duvvuru Saint Louis University, Bohan Zhang Saint Louis University, Missouri, Michael Vierhauser University of Innsbruck, Ankit Agrawal Saint Louis University, Missouri Pre-print Media Attached | ||
11:45 15mTalk | Efficient Domain Augmentation for Autonomous Driving Testing Using Diffusion Models Research Track Luciano Baresi Politecnico di Milano, Davide Yi Xian Hu Politecnico di Milano, Andrea Stocco Technical University of Munich, fortiss, Paolo Tonella USI Lugano Pre-print | ||
12:00 15mTalk | GARL: Genetic Algorithm-Augmented Reinforcement Learning to Detect Violations in Marker-Based Autonomous Landing Systems Research Track Linfeng Liang Macquarie University, Yao Deng Macquarie University, Kye Morton Skyy Network, Valtteri Kallinen Skyy Network, Alice James Macquarie University, Avishkar Seth Macquarie University, Endrowednes Kuantama Macquarie University, Subhas Mukhopadhyay Macquarie University, Richard Han Macquarie University, Xi Zheng Macquarie University | ||
12:15 15mTalk | Decictor: Towards Evaluating the Robustness of Decision-Making in Autonomous Driving Systems Research Track Mingfei Cheng Singapore Management University, Xiaofei Xie Singapore Management University, Yuan Zhou Zhejiang Sci-Tech University, Junjie Wang Tianjin University, Guozhu Meng Institute of Information Engineering, Chinese Academy of Sciences, Kairui Yang DAMO Academy, Alibaba Group, China | ||