Comprehensive Learning Particle Swarm Optimisation with Limited Local Search for UAV Path Planning

Unmanned Aerial Vehicles (UAVs) have been widely used due to their autonomy, maneuverability, low cost, and accessibility to areas inaccessible by humans or ground vehicles. Path planning is an essential part for UAVs. In this paper, we propose a new Comprehensive Learning Particle Swarm Optimisation with Limited Local Search (CLPSOLLS) algorithm to optimise UAV path planning problems. The algorithm improves accuracy with an order of magnitude less computational costs in difficult scenarios with limited degrees of freedom. The performance of the proposed CLPSOLLS is compared with the state of art variants of PSO on five scenarios of increasing complexity. The superiority of this algorithm is particularly apparent in difficult scenarios.