激光即时定位与建图算法综述

Summary of the Laser SLAM Algorithms

摘要:

激光SLAM(Simultaneous Localization andMapping)是一种在机器人导航和自主驾驶领域被广泛应用的技术；该技术可以利用激光雷达扫描环境并提取特征点,实现机器人的自主定位和地图构建；针对机器人激光SLAM技术进行研究,分析了各个激光SLAM算法的基本原理,并且对主流SLAM算法进行了现状总结；根据激光SLAM算法的特点以及原理不同,将激光SLAM算法分为:基于滤波器的算法、基于图优化的算法、基于配准的算法、基于学习的算法等；基于上述分类,详细介绍了每个算法的优缺点,并且分述了近两年的主要研究成果；针对移动机器人激光SLAM算法研究现状,对激光SLAM算法的未来发展进行了展望。

Abstract:

Laser SLAM (Simultaneous Localization and Mapping) is a widely used technology in the field of robot navigation and autonomous driving; The technique can use lidar to scan the environment and extract feature points, Realize the autonomous positioning and map construction of the robot; Research on the robotic laser SLAM technology, Analyzed the underlying principles of the various laser SLAM algorithms, And the mainstream SLAM algorithm is summarized; According to the characteristics and principles of the laser SLAM algorithm, The laser SLAM algorithm is divided into: filter based algorithm, graph optimization based algorithm, registration based algorithm, learning based algorithm and other algorithms; Based on the above classification, Details of the advantages and disadvantages of each algorithm, And described the main research results of the past two years; For the research status of laser SLAM algorithm in mobile robot, We discuss the future development of the laser SLAM algorithm.