同步定位与建图(Simultaneous Localization and Mapping，SLAM)技术可使自动驾驶车辆在未知环境中根据车载传感器采集到的数据估计自身位姿，建立环境地图，为车辆的规划、决策提供定位信息，是近年来自动驾驶技术研究的热点之一。基于车载激光雷达的点云数据，聚焦SLAM技术在自动驾驶领域的应用，围绕前端里程计、后端优化和回环检测技术，对国内外相关研究进行综述。考虑到单一传感器的局限性，结合目前多传感器融合研究的热点与难点，展望了自动驾驶多传感器融合SLAM技术在自动驾驶领域的机遇与挑战。
A Review of LiDAR-Based Simultaneous Localization and Mapping Methods for Autonomous Driving
Simultaneous localization and mapping(SLAM)technology enables autonomous vehicles to estimate their own poses and establish the map of an unknown environment according to the data collected by onboard sensors.SLAM can provide localization information to the decision-making module for vehicle planning,and has become one of the research hotspots of autonomous driving technology in recent years.Based on the point cloud data collected by LiDAR,this paper focuses on the SLAM technology applied in autonomous driving.The related research at home and abroad has been reviewed including the front-end odometry,the back-end optimization and loop closure detection.Due to the limitations of a single sensor,the opportunities and challenges of multi-sensor fusion SLAM technology for autonomous driving are discussed based on the research hotspots and difficulties in the field of multi-sensor fusion.
国家科技期刊平台
NSTL
万方数据
维普
