A Hybrid PSO-AOQPIO Approach for Efficient Wind-Affected UAV Task Allocation and Path Optimization

In this paper, a hybrid optimization algorithm has proposed, combining Particle Swarm Optimization (PSO) with Adaptive Operator Quantum-Behaved Pigeon Inspired Optimization (AOQPIO), to address the challenges of Unmanned Aerial Vehicle (UAV) task assignment and route planning under dynamic wind conditions. Traditional PSO is effective for global exploration but often struggles with local optimization, especially in dynamic environments influenced by wind. By integrating AOQPIO, which excels in local refinement, the proposed hybrid algorithm significantly improves convergence rate, solution quality, and robustness. The hybrid PSO-AOQPIO method achieves a final fitness value of 212.65 units in only 509 iterations, outperforming both standalone PSO and AOQPIO, which converge in 946 and 772 iterations, respectively. The hybrid algorithm also results in a 30.53% fitness improvement, significantly reducing the objective function (time) compared to PSO's and AOQPIO. Statistical significance tests further confirm the hybrid method's enhanced effectiveness in solving UAV optimization problems. This approach contributes a novel and efficient solution to UAV path planning, with potential applications in other dynamic and complex optimization problems.