基于改进粒子群算法的飞行器协同轨迹规划

考虑气动、轨迹、约束、指标间的耦合关系, 以多高超声速飞行器同时到达为目标建立了协同规划模型; 设计了一种自动满足终端约束的全新滑翔飞行剖面, 减少了规划算法需要处理的约束数量; 推导了滑翔段高精度解析解, 实现了过程约束和性能指标的快速求解; 提出了一种改进粒子群优化(Particle swarm optimization, PSO)算法, 借助强化学习方法构建协同需求与惯性权重间的动态映射网络, 提高了在线规划效率. 最后通过数学仿真验证了方法的正确性和有效性.

Synergistic Path Planning for Multiple Vehicles Based on an Improved Particle Swarm Optimization Method

This paper researches the synergistic flight for multiple hypersonic vehicles. The synergistic planning problem is formulated in view of the nonlinear coupling among aerodynamics, the performance index, and the path constraints. Then, the gliding profile, which naturally satisfies the terminal constraints and decreases the constraints, is proposed. Meanwhile, accurate solutions are deduced in the glide phase, so path constraints and the performance index can be quickly derived. An improved particle swarm optimization (PSO) method is developed by building the network between synergistic requirements and the optimal inertial weight in PSO based on a reinforcement learning method. Thus, the efficiency online computational efficiency can be largely improved. Numerical simulation results indicate the efficiency of the proposed method.