Research Of Multi-UAV Path Planning Based On Genetic Algorithm

Earthquake does great harm to human as one of natural disasters. China is a country where earthquakes happen frequently. When earthquake occurs, quick and effective rescue operations are required and disaster losses should be minimized. With the development of science and technology, especially the improvement of robot technology, more and more scientific and technological achievements are applied to earthquake rescue. The traditional way of earthquake rescue requires people take part in on-the-spot work personally, which causes a potential safe problem. The method by using multiple robots to cooperate with each other to finish the earthquake rescue work has become the development direction of earthquake rescue techniques.Based on the analysis of the development of robot technology, the thesis proposes a three-dimensional earthquake rescue program, and researches multi-UAV path planning technology. Multi-UAV path planning problem can be solved by double-goal MTSP. The paper firstly analyzes the features of genetic algorithm. Then a variety of coding programs of genetic algorithm are compared and evaluated, and relevant coding program, selection operator, crossover operator and mutation operator are designed according to the features of multi-UAV path planning. At last, the paper develops multi-UAV path planning simulation system, and the stability, availability and good commonality has been validated by a set of simulation instances.