Research on improved genetic simulated annealing algorithm for multi-UAV cooperative task allocation

Abstract

In order to solve the cooperative search problem of multiple unmanned aerial vehicles (multi-UAVs) in a large-scale area, we propose a genetic algorithm (GA) incorporating simulated annealing (SA) for solving the task region allocation problem among multi-UAVs on the premise that the large area is divided into several small areas. Firstly, we describe the problem to be solved, and regard the task areas allocation problem of multi-UAVs as a multiple traveling salesman problem (MTSP). And the objective function is established under the premise that the number of task areas to be searched by each UAV is balanced. Then, we improve the GA, using the advantages of the SA can jump out of the local optimal solution to optimize the new population of offspring generated by GA. Finally, the validity of the algorithm is verified by using the TSPLIB database, and the set MTSP problem is solved. Through a series of comparative experiments, the validity of GAISA and the superiority of solving the MTSP problem can be demonstrated.

High-Fidelity Decision-Making and Simulation for Cooperative Autonomous Air Combat Considering the Effect of Flight Controller

“…Hungarian algorithm [7] Optimized hybrid particle swarm optimization Less computation and higher efficiency Distributed algorithm [8] Low requirements for airborne hardware equipment Genetic algorithm [9]; Particle swarm optimization [10], [11]; Simulated annealing [12], [13] Faster convergence speed and less possibility of falling into local optimization network (BN) enables machines to take correct decisionmaking operations by emulating the expert's actions [2], [3], and is appropriate for air combat at various distances from a theoretical point of view [4], whereas the accuracy of decision highly depends on the the acquisition of empirical knowledge.…”

“…Negotiation method, such as distributed algorithm [8], has strong robustness but requires higher computing and communication ability of UAVs themselves. Swarm intelligence method, such as genetic algorithm [9], particle swarm optimization algorithm [10], [11], and simulated annealing algorithm [12], has the advantages of high convergence speed and simple operation, but may fall into local optimization and cause the decreased accuracy of the solution attributed to the randomness of initial settings [13].…”