Path planning and obstacle avoidance of unmanned aerial vehicle based on improved genetic algorithms

Path planning is always an essential issue and complicated optimum problem for unmanned aerial vehicle (UAV). Genetic algorithms are well applied to solve such problems as a stochastic search method. In this paper, a new method of path planning for UAV based on genetic algorithms is introduced. Reasonable coding way and fitness function are used in this improved genetic algorithm, and prior knowledge is added to the genetic algorithm. By selecting essential points and moving strategy in advance, this new method can highly reduce the computation cost and find the optimal path more efficiently. The simulation result shows that this new approach is proved to improve the search efficiency.