Imperialist competitive algorithm optimized artificial neural networks for UCAV global path planning

Unmanned combat aerial vehicle (UCAV), owing to its potential to perform dangerous, repetitive tasks in remote and hazardous, is very promising for the technological leadership of the nation and essential for improving the security of society. A novel hybrid method for the globally optimal path planning of UCAV is proposed in this paper, which is based on an artificial neural network (ANN) trained by imperialist competitive algorithm (ICA). The comparative experimental results with artificial bee colony (ABC) algorithm show that our proposed approach can not only reduce the uncertainty of the evolutionary computation caused by the probability model, but also avoid falling into local point with much quicker speed.