CAJ | 학술논문

为了解决在未知环境情况下障碍物运动状态的检测问题，提出一种基于激光雷达自主动态障碍物的检测方法。通过近邻域法和规则分类器算法对激光雷达检测的数据进行聚类；在此基础上分析了聚类障碍物的特征参数，利用聚类障碍物数据的置信区间关联性分析确定了障碍物的类型，对同一类型障碍物进行相对坐标转化分析确定了障碍物的速度、航向。实验结果表明；该方法能够在25 m s内实现对车辆通行区域内的障碍物进行有效的聚类，从而实现对同一障碍物速度和航向的检测。
위료해결재미지배경정황하장애물운동상태적검측문제，제출일충기우격광뢰체자주동태장애물적검측방법。통과근린역법화규칙분류기산법대격광뢰체검측적수거진행취류；재차기출상분석료취류장애물적특정삼수，이용취류장애물수거적치신구간관련성분석학정료장애물적류형，대동일류형장애물진행상대좌표전화분석학정료장애물적속도、항향。실험결과표명；해방법능구재25 m s내실현대차량통행구역내적장애물진행유효적취류，종이실현대동일장애물속도화항향적검측。
In order to detect the motion state of an obstacle in an unknow n environment ,a method for detecting dynamic obstacles by using laser radar is put forward .The close neighborhood method and the rules classifier algorithm are used to cluster the data obtained by the laser radar .And then the characteristic parameters of the clustering obstacles are analyzed .T he types of obstacles are determined by analyzing the confidence interval correlation of the clustering obstacle data , and the velocity and azimuth of the obstacles are determined by the relative coordinate transformation of the obstacles of the same type .The experimental results show that the method can effectively cluster the obstacles in the traffic region in 25ms ,so as to detect the velocity and azimuth of the same obstacle .