Environmental Perception of Multi-layer Laser Radar in a Driverless Car
-
摘要: 为了使无人驾驶车获得可行驶区域和障碍物信息, 通过分析大量激光雷达扫描点数据, 总结并得出路沿数据点独有的特征, 提出一种基于路沿数据点特征和多层融合技术的路沿检测算法.应用Dezert-Smarandache理论 (Dezert-Smarandache theory, DSm T) 对无人驾驶车前方道路环境建立栅格地图, 并利用证据理论中的冲突系数检测动态障碍物.最后, 采用膨胀算法、侵蚀算法和改进的八邻域区域标记算法对动态障碍物进行聚类和信息提取.实车实验结果表明:本算法可稳定、准确地感知无人驾驶车周围环境信息.Abstract: To obtain the information of drivable area and obstacles for a driverless car, unique characteristics of the road edge data points were summarized and concluded by analyzing a large number of scanning lidar data, and a road edge detection algorithm was proposed based on the features of road edge data points and multi-layer fusion technology. DSm T was applied to establish a grid map for the road environment in front of the unmanned vehicle. The DSm T conflict coefficient was used to detect dynamic obstacles. Finally, the clustering and information extraction of dynamic obstacles was completed by the expansion algorithm, erosion algorithm, and the improved eight neighborhood labeling algorithm.Resultsshow that the algorithm can stably and accurately perceive the environment information around driverless vehicle.
-
-
[1] 杨象军.基于四线激光雷达的道路检测与跟踪[D].杭州:浙江大学信息学部, 2013.YANG Xiang-jun.Road detection and tracking based on the four line laser radar[D].Hangzhou:Faculty of Information Technology, Zhejiang University, 2013. (in Chinese) [2] GIM Suhyeon, MEO Ilyas.Drivable road recognition by multilayered Li DAR and vision[J].Intelligent Autonomous Systems, 2013 (12) :43-56.
[3] 杨飞, 朱株, 龚小谨, 等.基于三维激光雷达的动态障碍实时检测与跟踪[J].浙江大学学报:工学版, 2012 (9) :18-24.YANG Fei, ZHU Zhu, GONG Xiao-jin, et al.Dynamic obstacle real-time detection and tracking based on threedimensional laser radar[J].Journal of Zhejiang University:Engineering Science, 2012 (9) :18-24. (in Chinese) [4] 都强, 杭柏林.最小二乘法在多传感器测量标定中的应用[J].传感技术学报, 2005 (2) :36-38.DU Qiang, HANG Bo-lin.The application of the least square method in multi-sensor measurement calibration[J].Journal of Sensing Technology, 2005 (2) :36-38. (in Chinese) [5] 曹红玉, 孙汉旭, 贾庆轩, 等.基于改进的D-S证据理论的栅格地图构建[J].吉林大学学报:工学版, 2011, 41 (4) :239-243.CAO Hong-yu, SUN Han-xu, JIA Qing-xuan, et al.Building a grid map based on the improved DS theory[J].Journal of Jilin University:Engineering Science, 2011, 41 (4) :239-243. (in Chinese) [6] MORAS Julien, CHERFAOUI Véronique, BONNIFAIT Philippe.Credibilist occupancy grids for vehicle perception in dynamic environments[C]∥2011 IEEE International Conference on Robotics and Automation.Shanghai:IEEE, 2011:84-89.
[7] 侯俊, 苗壮, 潘泉.DST与DSm T自适应融合算法[J].微电子学与计算机, 2006, 23 (10) :150-152.HOU Jun, MIAO Zhuang, PAN Quan.DST and DSm T adaptive fusion algorithm[J].Microelectronics and Computer, 2006, 23 (10) :150-152. (in Chinese) [8] 张云哲, 赵海, 宋纯贺, 等.一种新的连通区域标记算法[J].计算机应用研究, 2010 (11) :342-344.ZHANG Yun-zhe, ZHAO Hai, SONG Chun-he, et al.A new connected domain labeling algorithm[J].Application Research of Computers, 2010 (11) :342-344. (in Chinese) [9] 罗志灶, 周赢武, 郑忠楷.基于区域增长的连通域标记算法的优化[J].闽江学院学报, 2011 (2) :47-50.LUO Zhi-zao, ZHOU Ying-wu, ZHENG Zhong-kai.The optimization of connected domain labeling algorithm based on region growing[J].Journal of Minjiang University, 2011 (2) :47-50. (in Chinese)
计量
- 文章访问数: 12
- HTML全文浏览量: 13
- PDF下载量: 10