{"title":"Obstacle detection using a 2D LIDAR system for an Autonomous Vehicle","authors":"Angelo Nikko Catapang, M. Ramos","doi":"10.1109/ICCSCE.2016.7893614","DOIUrl":null,"url":null,"abstract":"Obstacle detection is a requirement for Advanced Driver Assistance Systems (ADAS) which are the precursors to autonomous vehicle systems. A number of sensor systems have been used before to perform obstacle detection. One particular sensor system is the LIDAR system which is noted for its accuracy in measuring distances. However, most commercially available LIDAR (Light Detection and Ranging) systems are expensive and computationally intensive. This research characterizes an inexpensive 2D LIDAR system using the LIDAR-Lite v1 for use in obstacle detection for autonomous vehicles. Since data acquisition occurs only in a single plane, the system should be computationally fast. The field of vision should be capable of up to 360 degrees. The data acquired was median-filtered and pre-processed by the merging and segmentation of data points. Obstacle detection was then performed via clustering. Results show that obstacles with widths of 1 meter can be detected at distances of 10 meters.","PeriodicalId":6540,"journal":{"name":"2016 6th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","volume":"100 1","pages":"441-445"},"PeriodicalIF":0.0000,"publicationDate":"2016-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"48","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 6th IEEE International Conference on Control System, Computing and Engineering (ICCSCE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCSCE.2016.7893614","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 48
Abstract
Obstacle detection is a requirement for Advanced Driver Assistance Systems (ADAS) which are the precursors to autonomous vehicle systems. A number of sensor systems have been used before to perform obstacle detection. One particular sensor system is the LIDAR system which is noted for its accuracy in measuring distances. However, most commercially available LIDAR (Light Detection and Ranging) systems are expensive and computationally intensive. This research characterizes an inexpensive 2D LIDAR system using the LIDAR-Lite v1 for use in obstacle detection for autonomous vehicles. Since data acquisition occurs only in a single plane, the system should be computationally fast. The field of vision should be capable of up to 360 degrees. The data acquired was median-filtered and pre-processed by the merging and segmentation of data points. Obstacle detection was then performed via clustering. Results show that obstacles with widths of 1 meter can be detected at distances of 10 meters.
先进驾驶辅助系统(ADAS)是自动驾驶汽车系统的前身,障碍物检测是ADAS的一项要求。在进行障碍物检测之前,已经使用了许多传感器系统。一种特殊的传感器系统是激光雷达系统,它以测量距离的准确性而闻名。然而,大多数商业上可用的激光雷达(光探测和测距)系统是昂贵的和计算密集型的。这项研究的特点是使用LIDAR- lite v1的廉价2D激光雷达系统,用于自动驾驶汽车的障碍物检测。由于数据采集只发生在一个平面上,所以系统的计算速度应该很快。视野应该能够达到360度。对采集到的数据进行中值滤波,并对数据点进行合并和分割预处理。然后通过聚类进行障碍物检测。结果表明,宽度为1米的障碍物可以在距离为10米的地方被检测到。