A Reinforcement Learning-Based Adaptive Grey Wolf Optimizer for Simultaneous Arrival in Manned/Unmanned Aerial Vehicle Dynamic Cooperative Trajectory Planning

Abstract

Highlights: What are the main findings? A novel reinforcement learning-based Grey Wolf Optimizer (RL-GWO) is proposed, which adaptively selects search strategies to balance exploration and exploitation. Experimental results show the proposed RL-GWO significantly outperforms standard GWO and DE in both convergence speed and final solution quality for cooperative path planning. What is the implication of the main finding? The proposed method provides a more efficient and robust solution for achieving high-precision time synchronization among heterogeneous UAVs in complex environments. The developed dual-layer dynamic planning framework demonstrates high practical value, enabling rapid and effective online replanning to ensure safety against sudden threats. Addressing the challenge of high-precision time-coordinated path planning for manned and unmanned aerial vehicle (UAV) clusters operating in complex dynamic environments during missions like high-level autonomous coordination, this paper proposes a reinforcement learning-based Adaptive Grey Wolf Optimizer (RL-GWO) method. We formulate a comprehensive multi-objective cost function integrating total flight distance, mission time, time synchronization error, and collision penalties. To solve this model, we design multiple improved GWO strategies and employ a Q-Learning framework for adaptive strategy selection. The RL-GWO algorithm is embedded within a dual-layer “global planning + dynamic replanning” framework. Simulation results demonstrate excellent convergence and robustness, achieving second-level time synchronization accuracy while satisfying complex constraints. In dynamic scenarios, the method rapidly generates safe evasion paths while maintaining cluster coordination, validating its practical value for heterogeneous UAV operations.