基于自然柱状特征地图的智能车定位

针对室外环境中手工测量柱状自然特征建立环境的特征地图(简称柱图)工作量大、精度低的问题，提出了一种基于激光雷达的地图自动生成方法.在此基础上，采用基于柱图的定位方法，使用迭代最近点算法进行地图匹配，提高了定位精度.仿真数据和实际数据的实验结果表明，该方法具有精度高、速度快等特点.

Natural Pole-map Dased Localization for Intelligent Vehicles

In order to overcome the big workload and low accuracy of measuring the pole map manually in outdoor environment, a laser radar based mapping method was presented. On the basis of this, a pole map based localization was introduced which does map matching using iterative closest points and can enhance the accuracy of localization. This method was tested on both synthetic and real range data collected in natural environment. The experimental results demonstrate its high accuracy, low computation and wide applicability.