• 全部
主办单位:煤炭科学研究总院有限公司、中国煤炭学会学术期刊工作委员会
基于LiDAR的煤矿井下自动驾驶边界检测与跟踪方法研究
  • Title

    LiDAR-based boundary detection and tracking method for autonomous vehicles in underground coal mines

  • 作者

    于淼张晞龚子任

  • Author

    YU Miao;ZHANG Xi;GONG Ziren;HUANG Lisha;MENG Junzhou;LI Huazhi;WANG Zhangyu

  • 单位

    中国矿业大学(北京)北京航空航天大学北京踏歌智行科技有限公司北京航空航天大学合肥创新研究院

  • Organization
    China University of Mining and Technology-Beijing
    Beihang University
    Beijing TageIDriver Technology Co. , Ltd.
    Hefei Innovation Research Institute of Beihang University
  • 摘要
    为了满足井下边界检测应用的迫切需求,提出一种基于LiDAR的边界检测与跟踪方法,该方法包含点云实时校正、点云栅格化、边界拟合以及边界跟踪四部分。针对井下道路边界不规则且坡度变化频繁的特征,设计一种点云实时校正方法,采用预校正和动态更新两个步骤实现地面点云和激光雷达坐标系平行。利用栅格思想将校正后点云映射到二维栅格图中,有效避免路面凹凸不平对边界提取的影响。针对弯道和硐室场景造成的边界缺失问题,采用卡尔曼滤波算法对点云进行稳定跟踪。在井下实车采集数据上的实验结果表明,本研究提出的算法可以准确检测并稳定跟踪双侧边界,在直道、弯道、硐室场景检测精度分别为97.5%,93.2%,88.3%,并且满足自动驾驶的实时性。
  • Abstract
    To meet the urgent demands in underground boundary detection, a method for boundary detection and tracking in underground mines is proposed, which is composed of four parts: real - time point cloud correction, point cloud gridding, boundary fitting and boundary tracking. Based on the characteristics of irregular boundaries and frequently changing slopes in underground roads, a real - time point cloud correction method is designed, which consists of pre - correction and dynamic update to achieve parallelism between the road point cloud and the LiDAR coordinate system. To avoid the influence of uneven road surfaces on boundary extraction, the corrected point cloud is projected into a two-dimensional gridding map. To solve the problem of blind areas caused by underground turnings and chambers, Kalman Filter is utilized to stably track the boundary point cloud. The performance of the proposed method is evaluated on the data collected in real-world operation scenarios. The experimental results demonstrate that the proposed method can detect and track underground boundaries, with the precision of 97. 5% for straight channels, 93. 2% for turnings and 88. 3% for chambers, as well as meet the real-time requirements in autonomous driving.
  • 关键词

    自动驾驶井工矿边界检测LiDAR

  • KeyWords

    autonomous driving; underground mine; boundary detection; LiDAR

  • DOI
  • 引用格式
    于 淼, 张 晞, 龚子任, 等. 基于 LiDAR 的煤矿井下自动驾驶边界检测与跟踪方法研究 [J]. 煤炭工程,2023, 55(6): 145-151.
  • 相关文章
相关问题

主办单位:煤炭科学研究总院有限公司 中国煤炭学会学术期刊工作委员会

©版权所有2015 煤炭科学研究总院有限公司 地址:北京市朝阳区和平里青年沟东路煤炭大厦 邮编:100013
京ICP备05086979号-16  技术支持:云智互联