Multi-UAV Optimization Method For Reliability-Aware Inspection

UAVs have the advantages of a wide field of view,great concealment and high efficiency.Thus,they are widely used in the field of autonomous monitoring.However,the limited range and the susceptibility to various types of failures seriously undermine the reliability of UAVs for inspection tasks,and damaged UAVs are difficult to repair,making them costly.In order to improve the reliability of UAVs and reduce costs,this paper investigates the optimization of UAV path planning and the quantity of UAVs for reliability inspections.The main research work in this paper is as follows:(1)A multi-UAV path planning method for reliability inspection has been proposed.By coordinating the flight paths of UAV groups,different UAVs can inspect the same task nodes to achieve the purpose of improving reliability.A multi-UAV collaborative inspection path planning model is established,the three-step optimal path planning solution method is designed based by greedy strategy.The simulation results show that the proposed method can not only improve the reliability of inspection task completion,but also effectively improve the speed of inspection tasks execution.(2)Because of the difficulty in repairing UAVs when they break down,the objective of both controlling the cost and improving the mission completion rate can be achieved if the right quantity of UAVs can be selected.This paper addresses the problem of UAVs cost optimization by first establishing a correlation model between the number of UAVs and the mission completion rate,and then,combining genetic algorithms and greedy algorithms to propose a three-step method to optimize the number of UAVs and their paths.Finally,fault-free UAVs will be assigned to perform the uncompleted tasks of abnormal UAVs.Simulation results show that the method proposed in this paper can find the least number of UAVs required to meet the task completion rate.(3)Physical experiments are conducted to validate the proposed method.The experimental results show that the method of this paper is still valid for practical inspection tasks.