Optimal Path Planning of Unmanned Combat Aerial Vehicle Using Improved Swarm Intelligence Algorithms

This study uses three improved Swarm Intelligence (SI) algorithms to apply to the optimal path planning of an unmanned combat aerial vehicle (UCAV) for achieving that the UCAV can availably avoid being detected or assaulted by enemy threat sources and safely arrive at given destination to perform its military mission. Generally, the optimal path planning is a NP-hard problem. To figure out the optimal solution of objective function accurately, this work adopts three improved SI algorithms, named Momentum-type Particle Swarm Optimization (Momentum-type PSO), Adaptive Cuckoo Search (Adaptive CS), and Rank-based Artificial Bee Colony (Rank-based ABC), to be the optimizers. The three improved algorithms all have excellent global search ability and computational efficiency. The simulation analyses include three scenarios which have different numbers and distributions of threat sources, domains of flight area, and locations of starting and target points of UCAV. The computed optimal paths obtained using the three improved algorithms will be compared with those obtained using other evolutionary methods in the literature.