自动驾驶汽车路径规划算法研究

Research on Path Planning Algorithm for Autonomous Vehicles

关于自动驾驶汽车技术的诸多研究中,路径规划是自动驾驶汽车的重要研究内容,也是当前自动驾驶汽车领域研究的热点之一,其目的是在一定环境场景下利用所选定的评价指标获得一条连接起始点与目标点的最优无碰撞路径。文章介绍了几种应用于路径规划的算法及其基本原理与特性,回顾了不同算法在自动驾驶汽车中的研究和应用,针对一些典型的优化方向对当前算法研究现状进行分析,通过完备性、概率完备性、最优性及渐进最优性4个评价指标对以上算法进行简单比较,并对自动驾驶汽车路径规划的未来研究方向做出展望。

Among many researches on self-driving car technology,path planning is an important research content of self-driving cars and one of the current hotspots in the field of self-driving cars.Its purpose is to obtain an optimal collision-free path connecting the starting point and the target point in a certain environmental scenario using the selected evaluation metrics.The article introduces several algorithms applied to path planning and their basic principles and characteristics,reviews the research and application of different algorithms in autonomous vehicles,analyzes the current status of algorithm research for some typical optimization directions,briefly compares the above algorithms by four evaluation indexes:completeness,probabilistic completeness,optimality,and asymptotic optimality,and makes an outlook on the future research of path planning for autonomous vehicles.The future research direction of autonomous vehicle path planning is also presented.