A novel reinforcement learning based grey wolf optimizer algorithm for unmanned aerial vehicles (UAVs) path planning

Abstract Unmanned aerial vehicles (UAVs) have been used in wide range of areas, and a high-quality path planning method is needed for UAVs to satisfy their applications. However, many algorithms reported in the literature may not feasible or efficient, especially in the face of three-dimensional complex flight environment. In this paper, a novel reinforcement learning based grey wolf optimizer algorithm called RLGWO has been presented for solving this problem. In the proposed algorithm, the reinforcement learning is inserted that the individual is controlled to switch operations adaptively according to the accumulated performance. Considering that the proposed algorithm is designed to serve for UAVs path planning, four operations have been introduced for each individual: exploration, exploitation, geometric adjustment, and optimal adjustment. In addition, the cubic B-spline curve is used to smooth the generated flight route and make the planning path be suitable for the UAVs. The simulation experimental results show that the RLGWO algorithm can acquire a feasible and effective route successfully in complicated environment.