UAV Cluster Task Assignment Algorithm Based on Improved Artificial Gorilla Troops Optimizer

Efficient task execution and optimized combat effectiveness can be achieved when a cluster of Unmanned Aerial Vehicles (UAVs) work collaboratively by assigning various tasks to each UAV reasonably. This paper suggests an algorithm for assigning tasks to a cluster of UAVs using an improved version of the Artificial Gorilla Troops Optimizer (GTO) that incorporates multiple strategies. The proposed algorithm adopts the Halton sequence to generate the initial population to ensure diversity. It uses an information sharing search strategy to enhance communication between the silverback gorilla and the population, effectively jumping out of the local optimal solution. In addition, the problem of inadequate solution accuracy caused by rapid convergence in the middle and later stages of iteration is improved using the golden sine strategy to coordinate GTO's global searching and local mining capabilities. Based on the experimental results, it has been determined that the proposed algorithm outperforms other swarm intelligence algorithms in terms of convergence value and rate across various test functions. Additionally, it has been found to achieve faster and more stable task assignment results.