基于人工势场引导进化算法的多飞行器冲突解脱方法

ircraft conflict resolution is a key technology for ensuring airspace safety. The classical conflict resolution approach, potential field (PF), can provide conflict-free paths, but it may result in unfeasible paths. On the other hand, the methods based on evolutionary algorithm cannot get satisfying solution in real time. In order to overcome these drawbacks, we proposed an improved potential field method. The solution obtained by PF is as priori knowledge, based on which the differential evolution (DE) algorithm is adopted to further optimization. Our method not only can reduce the searching space and obtain solutions in real time, but also can improve the solution quality. The experimental studies on classic scenario proved the improved PF performed much better than PF. What's more, the proposed method can also solve the conflict up to 16 aircraft in a short time.