面向无人驾驶矿车的露天矿山道路坡度实时检测方法

doi:10.11947/j.AGCS.2021.20210242

测绘学报 ›› 2021, Vol. 50 ›› Issue (11): 1628-1638.doi: 10.11947/j.AGCS.2021.20210242

• 智能驾驶环境感知 • 上一篇

面向无人驾驶矿车的露天矿山道路坡度实时检测方法

孟德将¹, 田滨^2,3, 蔡峰⁴, 高义军⁵, 陈龙⁶

1. 北京慧拓无限科技有限公司, 北京 100190;
2. 中国科学院自动化研究所复杂系统管理与控制国家重点实验室, 北京 100190;
3. 中国科学院大学人工智能学院, 北京 100190;
4. 中国中煤能源集团有限公司, 北京 100120;
5. 安徽马钢矿业资源集团南山矿业有限公司, 马鞍山 243031;
6. 中山大学数据科学与计算机学院, 广州 510006

收稿日期:2021-05-10 修回日期:2021-10-05 发布日期:2021-12-07
通讯作者: 田滨 E-mail:bin.tian@ia.ac.cn
作者简介:孟德将(1993—),男,硕士,高级工程师,研究方向为无人驾驶感知技术。
基金资助:
广东省重点领域研发计划（2020B0909050001）

Road slope real-time detection for unmanned truck in surface mine

MENG Dejiang¹, TIAN Bin^2,3, CAI Feng⁴, GAO Yijun⁵, CHEN Long⁶

1. Beijing Waytous Technologies Co., Ltd., Beijing 100190, China;
2. State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China;
3. School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100190, China;
4. China National Coal Group Corp., Beijing 100120, China;
5. Magang Group Nanshan Mine Co., Ltd., Ma'anshan 243031, China;
6. School of Data and Computer Science, Sun Yat-sen University, Guangzhou 510006, China

Received:2021-05-10 Revised:2021-10-05 Published:2021-12-07
Supported by:
Key-Area Research and Development Program of Guangdong Province (No. 2020B0909050001)

摘要/Abstract

摘要： 露天矿山大部分道路坡度大，无人驾驶矿车在上下坡之前如果不能合理规划速度，则容易发生一些危险，例如因下坡急减速导致的物料外撒或因上坡导致的溜车。无人驾驶矿车通过精确检测车辆前方一定范围内的道路坡度，可以在上下坡之前合理规划速度。目前无人驾驶矿车实时检测露天矿山道路坡度存在一些挑战：露天矿山道路坡度大且不平整，无人驾驶矿车在行驶过程中会有比较大的俯仰和弹跳运动，因为基于惯性导航系统（inertial navigation system，INS）或全球导航卫星系统（Global Navigation Satellite System，GNSS）的方法测出的是车辆的俯仰角，而不是所在道路区域的坡度；由于露天矿山几何特征缺失，这使得基于SLAM（simultaneous localization and mapping）的方法在特征缺失的路段容易匹配错误，而且基于SLAM的方法测出的也是车辆的俯仰角。本文针对目前无人驾驶矿车实时检测露天矿山道路坡度研究中存在的问题，提出了栅格卡尔曼道路坡度实时检测（grid Kalman road slope real-time detection，GKSRD）方法。该方法以三维激光雷达点云和INS俯仰角信息作为输入，并采用二维栅格地图、感兴趣矩形区域迭代优化算法和卡尔曼滤波器。相比于基于INS或GNSS的方法，该方法减小了无人驾驶矿车行驶过程中由于道路坡度大且不平整对道路坡度实时检测带来的误差。相比于基于SLAM的方法，因为该方法不依赖周围环境的几何特征，所以其不会受到露天矿山几何特征缺失的影响。通过试验验证，GKSRD方法对露天矿山道路坡度的实时检测平均误差小于0.01°，最大误差小于0.5°。相比于基于INS或GNSS的方法和基于SLAM 的方法，GKSRD方法精度更高，稳定性和环境适应性也更好。

关键词: 无人驾驶矿车, 道路坡度实时检测, 三维激光雷达, 露天矿山

Abstract: Given the steepness of road slope in surface mines, one unmanned truck may run at risk in unknown environment if it can’t plan a proper speed in advance. Therefore, it is crucial for an autonomous vehicle to perceive an accurate value of road slope of it in real time. However, the accuracy is hard to achieve in existing methods, including global navigation satellite system (GNSS), inertial navigation system (INS) and simultaneous localization and mapping (SLAM). For GNSS or INS, they can measure a truck’s angle of pitch, but this angle cannot be equal to road slope due to its large pitching and bouncing movements caused by steep and uneven roads. For the same reason, SLAM doesn’t work well either. Also, it will lose efficacy as geometric features are not obvious in open-pit mine. To deal with these challenges, this paper proposes a grid Kalman road slope real-time detection (GKSRD) method. The method’s input is 3D point cloud of lidar and the pitch of INS. And the method uses a 2D grid map, an iterative optimization algorithm in rectangular region of interest and the Kalman filter. Compared with methods based on GNSS or INS, this method minimizes the error of slope detection. Different from methods based on SLAM, this method does not rely on geometric features of the environment. Verified by experiments, the average error of the road slope detected by GKSRD method is less than 0.01 degree, and the maximum error is less than 0.5 degree. Hence, compared with methods based on INS or GNSS and methods based on SLAM, GKSRD method is more accurate, stable and adaptive.

Key words: unmanned truck, road slope real-time detection, 3D LiDAR, surface mine

中图分类号:

P227

孟德将, 田滨, 蔡峰, 高义军, 陈龙. 面向无人驾驶矿车的露天矿山道路坡度实时检测方法[J]. 测绘学报, 2021, 50(11): 1628-1638.

MENG Dejiang, TIAN Bin, CAI Feng, GAO Yijun, CHEN Long. Road slope real-time detection for unmanned truck in surface mine[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(11): 1628-1638.

参考文献

[1] SAHLHOLM P, JANSSON H, KOZICA E, et al. A sensor and data fusion algorithm for road grade estimation[J]. IFAC Proceedings Volumes, 2007, 40(10): 55-62.
[2] SAHLHOLM P, JOHANSSON K H. Road grade estimation for look-ahead vehicle control[J]. IFAC Proceedings Volumes, 2008, 41(2): 3380-3385.
[3] JO K, KIM J, SUNWOO M. Real-time road-slope estimation based on integration of onboard sensors with GPS using an IMMPDA filter[J]. IEEE Transactions on Intelligent Transportation Systems, 2013, 14(4): 1718-1732.
[4] BAE H S, RYU J, GERDES J. Road grade and vehicle parameter estimation for longitudinal control using GPS[C]//Proceedings of 2001 IEEE Intelligent Transportation Systems Conference. Oakland, CA, USA: IEEE, 2001: 166-171.
[5] JAUCH J, MASINO J, STAIGER T, et al. Road grade estimation with vehicle-based inertial measurement unit and orientation filter[J]. IEEE Sensors Journal, 2018, 18(2): 781-789.
[6] JI Kaijin, CHEN Huiyan, DI Huijun, et al. CPFG-SLAM: a robust simultaneous localization and mapping based on LiDAR in off-road environment[C]//Proceedings of 2018 IEEE Intelligent Vehicles Symposium. Changshu, China: IEEE, 2018: 650-655.
[7] ZHANG Ji, SINGH S. LOAM: LiDAR odometry and mapping in real-time[C]//Proceedings of 2014 Robotics: Science and Systems. Berkeley, California, USA: IEEE, 2014: 2-9.
[8] ZHANG Ji, SINGH S. Visual-lidar odometry and mapping: low-drift, robust, and fast[C]//Proceedings of 2015 IEEE International Conference on Robotics and Automation. Seattle, WA, USA: IEEE, 2015: 2174-2181.
[9] ZHANG Ji, SINGH S. Laser-visual-inertial odometry and mapping with high robustness and low drift[J]. Journal of Field Robotics, 2018, 35(8): 1242-1264.
[10] HESS W, KOHLER D, RAPP H, et al. Real-time loop closure in 2D LiDAr SLAM [C]//Proceedings of 2016 IEEE International Conference on Robotics and Automation. Stockholm, Sweden: IEEE, 2016: 1271-1278.
[11] ZHU Minzhao, YANG Yi, SONG Wenjie, et al. AGCV-LOAM: air-ground cross-view based LiDAR odometry and mapping[C]//Proceedings of 2020 Chinese Control and Decision Conference (CCDC). Hefei, China: IEEE, 2020: 5261-5266.
[12] YAN Li, DAI Jicheng, TAN Junxiang, et al. Global fine registration of point cloud in LiDAR SLAM based on pose graph[J]. Journal of Geodesy and Geoinformation Science, 2020, 3(2): 26-35.
[13] MA Biao, GUO Hongyan, ZHANG Huayu, et al. Estimation of road grade and vehicle velocity for autonomous driving vehicle[C]//Proceedings of the 43rd IECON Annual Conference of the IEEE Industrial Electronics Society. Beijing, China: IEEE, 2017: 4621-4626.
[14] HAO Shengqiang, LUO Peipei, XI Junqiang, et al. Estimation of vehicle mass and road slope based on steady-state Kalman filter[C]//Proceedings of 2017 IEEE International Conference on Unmanned Systems. Beijing, China: IEEE, 2017: 582-587.
[15] LIAO Xiaoyong, HUANG Qiuguang, SUN Dihua, et al. Real-time road slope estimation based on adaptive extended Kalman filter algorithm with in-vehicle data[C]//Proceedings of the 29th Chinese Control and Decision Conference. Chongqing, China: IEEE, 2017: 6889-6894.
[16] SEBSADJI Y, GLASER S, MAMMAR S, et al. Road slope and vehicle dynamics estimation[C]//Proceedings of 2008 American Control Conference. WA, USA: IEEE, 2008: 4603-4608.
[17] KIM M S, KIM B J, KIM C I, et al. Vehicle dynamics and road slope estimation based on cascade extended Kalman filter[C]//Proceedings of 2018 International Conference on Information and Communication Technology Robotics. Busan, Korea (South): IEEE, 2018: 6-8.
[18] ZHANG Ying, ZHANG Yingjie, AI Zhaoyang, et al. Estimation of electric mining haul trucks’ mass and road slope using dual level reinforcement estimator[J]. IEEE Transactions on Vehicular Technology, 2019, 68(11): 10627-10638.
[19] HU Mingxing, GAO Wengen, ZENG Yuxuan, et al. Vehicle mass and road grade estimation based on adaptive forgetting factor RLS and EKF algorithm[C]//Proceedings of the 5th International Conference on Power and Renewable Energy. Shanghai, China: IEEE, 2020: 342-346.
[20] TANG Jianlin, LU Xiaowei, AI Yunfeng, et al. Road detection for autonomous truck in mine environment[C]//Proceedings of 2019 IEEE Intelligent Transportation Systems Conference(ITSC). Auckland, New Zealand: IEEE, 2019: 839-845.
[21] YAO Wentao, DENG Zhidong, ZHOU Lipu. Road curb detection using 3D lidar and integral laser points for intelligent vehicles[C]//Proceedings of the 6th International Conference on Soft Computing and Intelligent Systems, and the 13th International Symposium on Advanced Intelligence Systems. Kobe, Japan: IEEE, 2012: 100-105.
[22] LYU Yecheng, BAI Lin, HUANG Xinming. Real-time road segmentation using LiDAR data processing on an FPGA[C]//Proceedings of 2018 IEEE International Symposium on Circuits and Systems. Florence, Italy: IEEE, 2018: 27-30.
[23] CHEN Zhe, ZHANG Jing, TAO Dacheng. Progressive LiDAR adaptation for road detection[J]. IEEE/CAA Journal of Automatica Sinica, 2019, 6(3): 693-702.
[24] CHEN Liang, YANG Jian, KONG Hui. Lidar-histogram for fast road and obstacle detection[C]//Proceedings of 2017 IEEE International Conference on Robotics and Automation(ICRA). Singapore: IEEE, 2017: 1343-1348.
[25] JASPERS H, HIMMELSBACH M, WUENSCHE H J. Multi-modal local terrain maps from vision and LiDAR[C]//Proceedings of 2017 IEEE Intelligent Vehicles Symposium (IV). Los Angeles, CA, USA: IEEE, 2017: 1119-1125.
[26] 周超, 曹志强, 孟祥瑞, 等. 面向斜坡区域的基于多线激光雷达的斜坡角度估计方法: 中国, CN201611052553.7[P]. 2016-11-24. ZHOU Chao, CAO Zhiqiang, MENG Xiangrui, et al. Slope angle estimation method based on multi-line Lidar for slope area:China, CN201611052553.7[P]. 2016-11-24.
[27] 肖强. 地面无人车辆越野环境多要素合成可通行区域检测[D]. 北京: 北京理工大学, 2015. XIAO Qiang. Multi-factor synthetic passable zone detection in off-road environment of ground unmanned vehicles[D]. Beijing: Beijing Institute of Technology, 2015.
[28] 邢贺, 黄海涵, 亢永, 等. 一种激光雷达和惯导联合标定的装置及标定方法: 中国,CN201922463317.X [P].2019-12-31. XING He, HUANG Haihan, KANG Yong, et al. The invention relates to an apparatus and a calibration method for the joint calibration of laser radar and inertial navigation: China, CN201922463317.X [P].2019-12-31.
[29] 季开进. 基于三维激光雷达的车辆定位研究[D]. 北京: 北京理工大学, 2019. JI Kaijin. Research on vehicle positioning based on 3D LiDAR[D]. Beijing: Beijing Institute of Technology, 2019.
[30] MENG Dejiang, TIAN Bin, PAN Ziyu, et al. Berm detection for autonomous truck in surface mine dump area[C]//Proceedings of 2021 IEEE International Intelligent Transportation Systems Conference (ITSC). Indianapolis, USA: IEEE, 2021: 2829-2834.

面向无人驾驶矿车的露天矿山道路坡度实时检测方法

Road slope real-time detection for unmanned truck in surface mine

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张烁, 陈丽平, 李铁映, 鄢咏折, 邓湘金, 顾征, 郑燕红, 马友青, 亓晨, 刘少创. 嫦娥五号探测器月面采样封装任务的定位精度[J]. 测绘学报, 2022, 51(5): 631-639.
[2]	唐晓芳, 詹总谦, 丁久婕, 刘佳辉, 熊子柔. 顾及超像素光谱特征的无人机影像自动模糊聚类分割法[J]. 测绘学报, 2022, 51(5): 677-690.
[3]	周宝定, 张文香, 黄金彩, 李清泉. 基于众源数据的室内外一体化行人路网构建[J]. 测绘学报, 2022, 51(5): 718-728.
[4]	王晨捷, 罗斌, 李成源, 王伟, 尹露, 赵青. 无人机视觉SLAM协同建图与导航[J]. 测绘学报, 2020, 49(6): 767-776.
[5]	王乐洋, 高华, 冯光财. 利用InSAR和GPS数据分析台湾西南两次M_w>6地震的触发关系及应力影响[J]. 测绘学报, 2019, 48(10): 1244-1253.
[6]	张恒璟, 崔东东, 程鹏飞. CORS站高程非线性速度场及方差波动模型构建方法[J]. 测绘学报, 2019, 48(9): 1096-1106.
[7]	赵建虎, 梁文彪. 海底控制网测量和解算中的几个关键问题[J]. 测绘学报, 2019, 48(9): 1197-1202.
[8]	陈张雷, 李崇辉, 郑勇, 陈冰, 何东汉. 天文定位中几何精度衰减因子最小值分析[J]. 测绘学报, 2019, 48(7): 879-888.
[9]	姚朝龙, 罗志才, 胡月明, 王长委, 张瑞, 李金明. 利用GPS垂向位移监测西南地区干旱事件[J]. 测绘学报, 2019, 48(5): 547-554.
[10]	鲁铁定, 吴光明, 周世健. 病态不确定性平差模型的岭估计算法[J]. 测绘学报, 2019, 48(4): 403-411.
[11]	贺礼家, 冯光财, 冯志雄, 高华. 哨兵-2号光学影像地表形变监测:以2016年M_W7.8新西兰凯库拉地震为例[J]. 测绘学报, 2019, 48(3): 339-351.
[12]	阮仁桂, 魏子卿, 贾小林. 一种基于星间单差模糊度固定的载波伪距生成方法[J]. 测绘学报, 2018, 47(12): 1591-1598.
[13]	李烁, 王慧, 耿则勋, 于翔舟, 卢兰鑫. 双范数混合约束的遥感影像亮度不均变分校正[J]. 测绘学报, 2018, 47(12): 1621-1629.
[14]	余建胜, 赵斌, 谭凯, 王东振. 汶川地震震后GNSS形变分析[J]. 测绘学报, 2018, 47(9): 1196-1206.
[15]	姜尚洁, 罗斌, 贺鹏, 杨国鹏, 顾亚平, 刘军, 张云, 张良培. 利用无人机多源影像检测车辆速度[J]. 测绘学报, 2018, 47(9): 1228-1237.