基于改进粒子群算法的无人机航迹规划

针对当前基本粒子群算法无人机航迹规划在后期收敛速度比较慢、效率不高、易陷入局部最优等问题,提出一种改进粒子群算法。首先,在迭代前期和后期分段设置惯性权值的调整,实现粒子惯性和寻优行为的平衡;其次,设置一个定值与相邻2次适应度函数最优值比较策略,防止陷入局部最优;最后,引入遗传算法的交叉、变异机制,得出更优的结果。并通过仿真验证了改进粒子群算法在三维空间航迹规划的有效性和可行性。结果表明,与其他航迹规划算法相比,新算法具有路径长度更短、耗时更少、路径更平滑等优点,加快了收敛速度,提高了航迹规划效率和稳定性。因此,改进算法的航迹规划可得到满足约束关系的最优航迹,对实现自主飞行有重要的参考价值。

UAV flight path planning based on improved particle swarm optimization

Aiming at the problems of slow convergence, low efficiency and easy to fall into local optimum for the UAV flight path planning of basic particle swarm optimization, an improved method is provided. Firstly, the adjustment of the inertia weight is set in the early and late stages of the iteration to achieve the balance between particle inertia and optimization behavior. Secondly, a comparison strategy is set between the fixed value and the adjacent two fitness function optimal values to prevent falling into local optimum. Finally, the crossover and mutation mechanism of the genetic algorithm is introduced to get better results. The effectiveness and feasibility of the improved particle swarm optimization algorithm in 3D space track planning are verified by simulation results. Compared with other track planning algorithms, it has the advantages of shorter path length, less time-consuming, smoother path, etc., which accelerates the convergence speed and improves the overall efficiency and stability. The flight path planning based on the improved algorithm can obtain the optimal flight path satisfying the constraint relation, which has important reference value for realizing autonomous flight.