Genetic Algorithm Based on Opposite Chromosome Multiple Genetic Operations Combined with Task Load Balancing

Abstract

A collaborative optimization method for task allocation and path planning in multi-UAV execution of multi-objective cooperative inspection tasks is proposed. The method is based on the Opposite Genetic Algorithms (OGA), which combines the actual task completion time with the balance of UAV inspection flight time, fault downtime, and maximum-minimum time load. A Task Balancing Opposite Chromosome Multiple Mutation Operator Genetic Algorithm (TOMGA) is introduced to solve the task load balancing problem by optimizing the task allocation among multiple UAVs with time as the optimization objective. Simulation results demonstrate that, this algorithm can effectively allocate inspection tasks to UAVs and generate initial flight routes. It resolves the issue of task load imbalance, improves the rationality of task allocation, enhances convergence speed, and overcomes the problem of local optima.