Path Planning for Unmanned Aerial Vehicle Based on Genetic Algorithm & Artificial Neural Network in 2D

The planning of path for UAV is always considered to be a critical task. Path planning for UAV in multiple missions can be accomplished by finding the solution for an optimization problem. Genetic Algorithm which is a global optimization tool can be used to solve the optimization problem for path planning of UAV. Artificial Neural Networks (ANN) is good at function fitting quickly and can be used to approximate almost any function. The Genetic Algorithms are good at converging to the global optimum solution generation by generation. Neural Networks work faster than Genetic Algorithms but may converge at local optimum. In this paper a new method for path planning of UAV for escaping from obstacle based on the combination of Genetic Algorithms and Artificial Neural Networks has been proposed in which the output generated from the Genetic Algorithms is used to train the network of Artificial Neural Networks. The model for path planning is based on 2D digital map.