[供应链调度]无反射板激光导航机器人地图创建的特征提取

针对无反射板激光导航机器人地图创建的直线特征提取，采用逐步分解的方法，将直线特征提取分为断点检测、线段分割、直线提取三个步骤逐步分离点集。首先采用自适应阈值法进行断点检测；然后基于迭代适应点算法进行点集分离、线段分割；最后采用最小二乘法拟合直线并结合区域搜索法进行优化，进一步提高直线特征提取的精度。实验表明，算法的重复定位精度在±6 mm以内，特征提取时间不大于0.02 s，满足机器人的实际导航需求。

Feature Extraction for Map Building of Automated Guided Robot Based on Laser Navigation without Reflector

To realize the line feature extraction of map building for laser navigation robot without reflector，a stepwise decomposition method was proposed herein.The line feature extraction method was divided into 3 steps: breakpoint detection，line segmentation，and line extraction.Firstly，an adaptive threshold method was used to detect the breakpoints.And then，a point set was separated，and the line segment was segmented based on the iterative adaptive point algorithm.Finally，a least square method was used to fit the lines，and the region search method was used to optimize the line feature extraction.Experiments show that the repetitive positioning accuracy of the algorithm is within ±6mm and the feature extraction time is not longer than 0.02s，which meets the actual navigation requirements of robots.