3D LIDAR based precise vehicle localization using fire extinguisher lamp in road tunnel

被引：1

作者：

Im J.-H. ^{[1
]}

Im S.-H. ^{[2
]}

Jee G.-I. ^{[1
]}

机构：

[1] Department of Electronics Engineering, Konkuk University

来源：

Journal of Institute of Control, Robotics and Systems | 2018年 / 24卷 / 08期

关键词：

3D LIDAR; Fire extinguisher lamp; Road tunnel; Tunnel shape information; Vehicle localization;

D O I：

10.5302/J.ICROS.2018.18.0081

中图分类号：

学科分类号：

摘要：

Vehicle localization is essential for autonomous driving. Basically, the position information of the autonomous vehicle is obtained from the Global Positioning System (GPS). More accurate localization can be performed by using maps and various sensors that are mounted on the autonomous vehicle. GPS receivers cannot receive GPS signals in tunnels, so dead reckoning (DR) is used for vehicle localization. However, the error from DR continuously accumulates. Therefore, this error must be corrected by using vehicle-mounted sensors, such as Light Detection and Ranging (LIDAR) and cameras. Tunnels have very specific shape information, which is usually an ellipse, and several emergency facilities exist in tunnels. Some facilities are separated from the tunnel wall, which can be detected by using 3D LIDAR. In particular, fire extinguisher lamps are periodically installed at intervals of 50 m, which can serve as good landmarks. First, the point cloud for the tunnel wall must be removed to effectively detect fire extinguisher lamps. This process can be easily conducted by using shape information. After this removal, we detect the fire extinguisher lamps. In this paper, we propose a 3D LIDAR-based vehicle-localization method that uses ellipse parameters and fire extinguisher lamps in road tunnels. These experiments are conducted at the Maseong tunnel in South Korea. The experimental results show that the root mean square (RMS) position errors in the lateral and longitudinal directions were 0.06 m and 0.23 m, respectively, exhibiting precise localization accuracy. © ICROS 2018.

引用

页码：703 / 709

页数：6

共 9 条

[1]

Ballingall S., Vehicle Positioning for C-ITS in Australia (Background Document), (2013)

[2]

Lee M.-H., Hur S.-J., Park Y.-W., Obstacle Classification Method using Multi Feature Comparison Based on Single 2D LiDAR,, Journal of Institute of Control, Robotics and Systems, 22, 4, pp. 253-265, (2016)

[3]

Fang T.-H., Han J.-W., Son N.-S., Kim S.-Y., Track Initiation and Target Tracking Filter Using LiDAR for Ship Tracking in Marine Environment,, Journal of Institute of Control, Robotics and Systems, 22, 2, pp. 133-138, (2016)

[4]

Im J.-H., Im S.-H., Song J.-H., Jee G.-I., 3D LIDAR based Precise Vehicle Localization Using Vertical Structure Landmarks in an Urban Area,, Journal of Institute of Control, Robotics and Systems, 23, 12, pp. 1116-1125, (2017)

[5]

Duff E.S., Roberts J.M., Corke P.I., Automation of an underground mining vehicle using reactive navigation and opportunistic localization,, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, (2003)

[6]

Tardioli D., Villarroel J.L., Odometry-less localization in tunnel-like environments,, 2014 IEEE International Conference on Autonomous Robot Systems and Competitions, (2014)

[7]

Larson J., Okorn B., Pastore T., Hooper D., Edwards J., Counter tunnel exploration, mapping, and localization with an unmanned ground vehicle,, Proc. SPIE 9084, (2014)

[8]

Ozaslan T., Loianno G., Keller J., Taylor C.J., Kumar V., Wozencraft J.M., Hood T., Autonomous navigation and mapping for inspection of penstocks and tunnels with MAVs,, IEEE Robotics and Automation Letters, 2, 3, pp. 1740-1747, (2017)

[9]

Daoust T., Pomerleau F., Barfoot T.D., Light at the end of the tunnel: high-speed lidar-based train localization in challenging underground environments,, Conference on Computer and Robot Vision, (2016)

← 1 →