The path planning of unmanned aerial vehicles (UAVs) in the threat and countermeasure region is a constrained nonlinear optimization problem with many static and dynamic constraints. The fruit fly optimization algorithm (FOA) is widely used to handle this kind of nonlinear optimization problem. In this paper, the multiple swarm fruit fly optimization algorithm (MSFOA) is proposed to overcome the drawback of the original FOA in terms of slow global convergence speed and local optimum, and then is applied to solve the coordinated path planning problem for multi-UAVs. In the proposed MSFOA, the whole fruit fly swarm is divided into several sub-swarms with multi-tasks in order to expand the searching space to improve the searching ability, while the offspring competition strategy is introduced to improve the utilization degree of each calculation result and realize the exchange of information among various fruit fly sub-swarms. To avoid the collision among multi-UAVs, the collision detection method is also proposed. Simulation results show that the proposed MSFOA is superior to the original FOA in terms of convergence and accuracy.

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.