中文摘要：

为解决无人水面艇自主避碰决策中的全局路径规划问题，提出一种基于电子海图栅格化建立环境模型的遗传算法全局路径快速搜索方法。通过对电子海图数据中的海洋环境信息进行提取，采用栅格法建立路径搜索空间的环境模型，并使用栅格标号对路径个体进行编码，利用一种随机快速搜索产生初始种群的改进遗传算法进行路径搜索，提高无人水面艇全局路径规划的收敛速度和优化效率。试验结果表明，采用改进遗传算法进行基于电子海图栅格化的无人艇全局路径规划具有一定的合理性和有效性。

英文摘要：

A global path fast search method based on genetic algorithm is proposed for the Unmanned Surface Vehicle （USV） to avoid collision autonomously. The environment model is established by rasterizing electronic chart. Marine environment information in electronic chart data is extracted. Path search space is constructed. Path individual is encoded according to the code of grid. An improved genetic algorithm that adopts heuristic random initialization population method to generate initial population is used to achieve the convergence speed and optimization efficiency of USV global path planning. The effectiveness and practicality of the algorithm are verified by experiments.