A Q-learning-based hybrid search algorithm integrating PRM and ACO for 3D UAV path planning

Key Points

• The algorithm significantly improves path planning efficiency in three-dimensional environments, optimizing UAV routes.
• Key performance metrics show a reduction in path length and computational time by up to 30% compared to traditional methods.
• This analysis employs a q-learning-based approach, combining probabilistic roadmap (PRM) and ant colony optimization (ACO) techniques.
• These findings support more efficient UAV navigation, indicating potential advancements in autonomous systems.