基于激光扫描雷达的矿井机车障碍物检测方法研究  

Research on Obstacle Detection Method for Mine Locomotive Based on Lidar

作　　者：方崇全 Fang Chongquan1,2(1. Chongqing Research Institute, China Coal Technology and Engineering Group, Chongqing 400039, China; 2. State Key Laboratory of the Gas Disaster Detecting, Preventing and Emergency Controlling, Chongqing 400037, Chin)

机构地区：[1]中煤科工集团重庆研究院有限公司,重庆400039 [2]瓦斯灾害监控与应急技术国家重点实验室,重庆400037

出　　处：《煤矿机械》2018年第8期32-34,共3页Coal Mine Machinery

基　　金：重庆市社会民生科技创新专项基金资助项目(cstc2016shmszx0008)

摘　　要：针对当前矿井机车防撞系统障碍物检测方法中存在的测距方法精度低、测距范围有限或者需要外加光源等问题,提出了一种基于激光扫描雷达的障碍物检测方法,该方法可实现机车270°范围内障碍物检测,检测范围广且无需外接光源。通过分析激光扫描雷达在巷道中的点云成像图的特征,提出了基于5点多边形的告警区域配置方法。利用射线法,实现了告警区域内的障碍物检测。使用C#实现了所提出的算法并编写了相关操作显示界面,在实验室环境中进行了障碍物检测实验。测试结果表明,所提出的方法能够有效、快速地识别障碍物并进行告警,障碍物检测时间小于1 s。To solve the problems of low accuracy, limited range or need for external light sources in the obstacle detection method of the mine locomotive collision avoidance system,propose an obstacle detection method based on lidar sensor, which can achieve obstacle detection within 270° surrounding of the mine locomotive. The detection range is wide and no external light source is required. By analyzing the features of the point cloud imagery of the lidar in the tunnel, the warning area configuration method based on five-point polygons is proposed. Using the classical ray casting method,obstacle detection in the warning area is achieved. The proposed method is implemented using C#along with the relevant operation and display interface. The obstacle detection experiment is performed in a laboratory environment. Test results show that the proposed method can effectively and quickly identify obstacles and provide warnings. The obstacle detection time is less than 1 second.

关 键 词：矿井机车 障碍物检测 激光扫描雷达 射线法 

分 类 号：TD524.3[矿业工程—矿山机电] TP391.41[自动化与计算机技术—计算机应用技术]