Multi-Target Round-Up Allocation Strategy for Unmanned Aerial Vehicle Swarm Based on Improved Adaptive Genetic Algorithm

Aiming at the multi-target round-up allocation for unmanned aerial vehicle (UAV) swarms, this paper proposes a multi-target round-up allocation strategy for UAV swarms based on an improved adaptive genetic algorithm. Firstly, to accelerate the convergence of the genetic algorithm and inhibit the “early maturity” to maintain the diversity of the population, the genetic algorithm was improved by combining the evolutionary stage, individual fitness value, and individual similarity. Secondly, based on the improved genetic algorithm, multiple independent round-up teams are generated by considering the three elements of total distance traveled, completion rate, and success rate. Thirdly, the Hungarian algorithm is used to allocate the round-up points within the round-up teams, and the correspondence between UAV and round-up points is established with the goal of the shortest total distance traveled by the teams so that each UAV only needs to arrive at the corresponding round-up point to complete the multi-target round-up task. Simulation results show that the adaptation value of the proposed round-up allocation strategy is 16.77% and 22.78% higher than that of the IAGA algorithm and the TAGA algorithm respectively, and the superiority of the proposed round-up allocation strategy is verified in the simulation experiments of two application scenarios.