Research On Fast Path Planning Method Based On Genetic Algorithm

With the performance of UAV continued to improve, the complexity of the tasks entrusted to it become higher and higher, making its route planning more complex and time consuming. To enhance the real time planning ability of existing system , a Fast Route Planning method Based on hierarchical strategy, and an implementation of its global planning was proposed; further more a fast path planning method based on virus-evolutionary genetic algorithm was developed. In order to improve the existing multi-track route planning capacity, a multi-objective optimization-based path planning method was given.All methods presented in this Dissertation were on the basis of analyzing and summarizing of previous studies ,aimed at practical application of specific engineering projects. Including the following part:(1) For the purpose of the fast route planning, the historical development of unmanned aerial vehicles was reviewed, the existing research results on route planning are analyzed and summarized. the family of evolutionary algorithms (EAs) were introduced combined with the author's opinion.(2) Go into particulars about a hierarchical planning method especially on its thinking of hierarchical strategy. The hierarchical planning method efficiently handled path constraints by dividing the whole planning process in two steps: global planning and local planning. Employing a hierarchical strategy, this method efficiently reduced computation complexity.(3) The genetic algorithm used in global planning was well known for the problems of premature and weakness in local searching. To overcome the problems,a fast path planning method based on virus-evolutionary genetic algorithm was proposed. Simulation results show that given the same path constraints it can generate a satisfactory path using much less time.(4)Under the hierarchical path planning framework, a multi-objective optimization-based path planning method was proposed. Analysed of the sea route planning constraints, introduced the GA multi-objective optimization to track evaluation process, making it a multi-objective planner. Experiments show that the method can generate pareto optimal tracks for the two main objectives, meeting all constraints.