Pseudo-Random UAV Test Generation Using Low-Fidelity Path Simulator

Shrinah, Anas, Eder, Kerstin

arXiv.org Artificial Intelligence 

--Simulation-based testing provides a safe and cost-effective environment for verifying the safety of Uncrewed Aerial V ehicles (UA Vs). However, simulation can be resource-consuming, especially when High-Fidelity Simulators (HFS) are used. T o optimise simulation resources, we propose a pseudo-random test generator that uses a Low-Fidelity Simulator (LFS) to estimate UA V flight paths. T est cases predicted to cause safety violations in the LFS are subsequently validated using the HFS. This paper presents PRGenUA V -LFS, a test generation tool that participated in the UA V Testing Competition organised by the Search-Based and Fuzz Testing (SBFT 2025) workshop [3].