Real-Time Path Planning for Autonomous UAVs: An Event-Triggered Multimodal Adaptive Pigeon-Inspired Optimization Approach

Path planning is both a substantial issue and an essential component of intelligent decision-making technology in uncrewed autonomous systems. This article investigates a real-time path planning algorithm for autonomous uncrewed aerial vehicles (UAVs). A cooperative path planning model is proposed that accounts for radar threats, dynamic targets, UAV collaboration, and complex constraints. Then, an event-triggered multimodal adaptive pigeon-inspired optimization (ET-MAPIO) algorithm is proposed. Specifically, a multimodal state update system and adaptive inertia weights are introduced to overcome the issues of local optima and sluggish convergence in existing bioinspired optimization methods. Furthermore, an event-triggered mechanism is developed to facilitate rapid and efficient path replanning in the presence of moving targets. Finally, simulation results demonstrate the optimality, real-time performance, and efficiency of the ET-MAPIO algorithm. Our approach is scalable in larger scale scenarios and outperforms the state-of-the-art technologies.