摘要：This paper considered the constrained unmanned aerial vehicle (UAV) path planning problem as the multi-objective optimization problem, in which both costs and constraints are treated as the objective functions. A novel multi-objective particle swarm optimization algorithm based on the Gaussian distribution and the Q-Learning technique (GMOPSO-QL) is proposed and applied to determine the feasible and optimal path for UAV. In GMOPSO-QL, the Gaussian distribution based updating operator is adopted to generate new particles, and the exploration and exploitation modes are introduced to enhance population diversity and convergence speed, respectively. Moreover, the Q-Learning based mode selection logic is introduced to balance the global search with the local search in the evolution process. Simulation results indicate that our proposed GMOPSO-QL can deal with the constrained UAV path planning problem and is superior to existing optimization algorithms in terms of efficiency and robustness.
