Opposite and Chaos Searching Genetic Algorithm Based for UAV Path Planning

One of the most challenges in Unmanned Aerial Vehicles (UAV) system is path planning, as it provides basic navigation for UAVs to accomplish various missions under different backgrounds. Genetic algorithm (GA) is an efficient swarm intelligence algorithm in solving combinational optimization problems. To realize more rapid and efficient path planning under the limitation of multiple obstacles, this paper presents a novel genetic algorithm, namely Opposite and Chaos searching Genetic Algorithm (OCGA). At initial stage, population are generated by opposite and chaos searching for better optimization ability. At iteration stage, the algorithm updates population with a crossover operator improved by teaching-learning based optimization's (TLBO) learning strategy to increase convergence and prevent local optima. Simulation results validate the performance of proposed algorithm is superior to Triple-colony Ant Optimization (TP-ACO) in terms of optimization ability and convergence speed.