基于协同进化的复杂低空下多飞行器协同航迹规划方法

Complex Low-Altitude Airspace Multi-aircraft Cooperation Path Planning Method Based on Cooperative Coevolutionary

由于低空空域环境复杂,威胁通用航空器运行安全。复杂低空多飞行器航迹规划方法是保障安全、提高效率的关键技术。在特定空域范围内,依据地形特点、环境威胁以及飞行器自身物理条件等约束和安全效率等性能指标,为飞行器规划出最优航迹。然而,多飞行器的航迹规划问题存在多约束、强耦合、多目标等难点,现有方法缺乏对问题先验知识的挖掘和利用,导致难以兼顾安全与效率。针对多飞行器航迹规划问题,建立了多飞行器航迹优化多目标模型。为了进一步提升优化效率,基于启发式算子的自适应差分多目标进化算法,引入多种群协同进化,每个飞行器通过不同种群独立进化,建立合作机制提升种群进化质量,避免陷入极值。最后通过二维与三维仿真实验验证了算法的可行性和有效性。

The situation under low-altitude airspace is much more complex and dangerous,and especially it is difficult to keep safety of aircraft when many aircraft are in a limited airspace. Therefore,it is necessary and important to develop path planning methods under low-altitude airspace which is the key technology to keep aircraft safety. Path planning for aircraft under the low-altitude airspace is to optimize the paths for aircraft with consideration of avoiding the obstacles and satisfying the physical constraints of aircraft. However,it is difficult to solve the characteristics such as multi-objective,many constraints and tightly coupled. Path planning for multi-aircraft under the low-altitude airspace is researched. An adaptive multi-objective evolutionary algorithm with heuristics operator and adaptive differential evolution multi-objective algorithm is propsed. The model of collision avoidance for aircraft is established firstly. Then,the cooperative coevolution is introduced to the proposed method. Each aircraft optimizes its path by using the multi-objective optimization algorithm,and avoids collision through cooperation among different aircraft. The experimental results show the proposed method is effective and can obtain optimal paths for aircraft in real time.