基于改进人工鱼群算法的无人机三维航迹规划

Three-dimensional Trajectory Planning for Unmanned Aerial Vehicles Based on Improved Artificial Fish Swarm Algorithm

无人机航迹规划算法中,针对传统人工鱼群算法(Artificial Fish Swarm Algorithm,AFSA)存在易陷入局部最优、优化效率不佳等问题,引入了步长衰减函数,提出了一种自适应步长的人工鱼群算法(Adaptive Step Size Artificial Fish Swarm Algorithm,AS-AFSA),实现航迹规划中全局与局部收敛的自适应;进一步给出了人工鱼权重优化策略,提高人工鱼群算法的收敛速度与精度。仿真结果表明,改进人工鱼群算法在无人机航迹规划情景下表现优异,迭代次数相同条件下,航迹代价相较于狼群算法(Wolf Colony Algorithm,WCA)优化了4.5%,相较于传统人工鱼群算法优化了2.5%。

In the unmanned aerial vehicle(UAV)trajectory planning algorithm,to address the issues of easily falling into local optima and inefficient optimization in the traditional artificial fish swarm algorithm(AFSA),a step size attenuation function is introduced,and an adaptive step size artificial fish swarm algorithm(AS-AFSA)is proposed to achieve adaptive convergence in both global and local aspects of trajectory planning.Furthermore,an optimization strategy for the individual fitness weight of artificial fish is provided to improve the convergence speed and accuracy of the AFSA.Simulation results show that the improved algorithm performs exceptionally well in UAV trajectory planning scenarios.Under the same number of iterations,the fitness is improved by 4.5%compared to the wolf colony algorithm(WCA)and 2.5%compared to the traditional AFSA.