Research On Multi-uavs Task Assignment And Dynamic Route Planning Based On Improved Genetic Algorithm

With the rapid development of science and technology,UAVs play a more and more important role in the military,and as the core components,route planning and task assignment are indispensable technical means to realize automatic navigation.Therefore,it is of great theoretical and practical significance to study this problem.The research content of this paper mainly includes the following three aspects:（1）The route planning and dynamic obstacle avoidance algorithms for UAVs are studied.In global route planning,an improved genetic algorithm is proposed.The deletion operator is added in the traditional genetic algorithm to shorten the path distance.At the same time,the roulette method is improved into the directional selection method.Then the total cost function is established according to the range,smoothness and safety.The optimal route is obtained and smoothed.In local route planning,The candidate route is generated by the cubic spline method and the optimal candidate route is selected by the total cost function.Simulation results show that the algorithm is optimized in the aspects of route length,running time and iteration times,and avoids the sudden threat.（2）The route planning of multiple UAVs under mobile threat is studied.The objective function model of multi UAVs route planning is established.And the cost function of obstacle avoidance safety is established.The optimal route line is selected according to the total objective function.The simulation results show that the improved genetic algorithm can complete the multi UAVs route planning,and the obstacle avoidance algorithm can avoid the moving threat better.（3）The problem of collaborative task assignment of multiple UAVs attacking ground moving targets is studied and a new method is proposed.A time-dependent task assignment prediction model is established.First,relevant sub-cost functions and benefit functions are established based on environmental information.It includes the health status of our UAV,the health status of enemy targets,the cooperative range cost of UAV and the attack benefit function of UAV,and the overall target function is established.Finally,an improved genetic algorithm is used to solve the problem.The method can get the best task assignment scheme,and the validity and applicability of the method are verified.