Natural Terrain Detection and SLAM Using LIDAR for UGV

  • Kuk Cho
  • SeungHo Baeg
  • Sangdeok Park
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 193)


This paper describes a natural terrain detection algorithm and a SLAM algorithm using a LIDAR sensor for an unmanned ground vehicle. We describe how features are detected from natural terrain, and then we localize the vehicle’s position and compose a map with the detected features. The LIDAR equipped on the experimental vehicle to scan natural terrain. The scan data is included many kinds of intrinsic disturbance on uneven terrain: a banded tree, a branch of a tree, uniform size of bush, undefined or unexpected objects. We apply a RANSAC (RANdom SAmple Consensus) algorithm to discriminate ground point cloud data and object point cloud data, and then separate bush point cloud data and tree point cloud data by two combination algorithms; GMM (Gaussian Mixture Model) and EM (Expectation Maximization). Both GMM and EM algorithms are for extracting features and classifying groups, respectively. We propose the double FCM (Fuzzy C-mean clustering) algorithm to robustly estimate the number of trees and its position. The Extended Kalman Filter approach to simultaneous localization and mapping (EKF-SLAM) is composed of extracted tree features. The mahalanobis distance is applied to remain consistency for feature correspondence which is for data association. Finally, we show the results which is experienced in a tree-filled mountain.


object detection SLAM natural terrain extended Kalman filter data association 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Vandapel, N., Huber, D.F., Kapuria, A., Hebert, M.: Natural Terrain Classication using 3-D Ladar Data. In: Proceeding of IEEE Int. Conf. on Robotics and Automation, ICRA 2004 (2004)Google Scholar
  2. 2.
    Lalonde, J.F., Unnikrishnan, R., Vandapel, N., Hebert, M.: Scale selection for classification of point-sampled 3D surfaces, 3-D Digital Imaging and Modeling. In: Fifth International Conference on 3DIM 2005, June 13-16 (2005)Google Scholar
  3. 3.
    Cho, K., Baeg, S.H., Park, S.D.: Multiple object detection and tracking on the uneven terrain using multiple lidar for UGV. In: Proceeding SPIE Defense Sensor and Security, March 26-30 (2012)Google Scholar
  4. 4.
    Fischler, M.A., Bolles, R.C.: Random Sample Consensus: “A paradigm for model fitting with applications to image analysis and automated cartography”. Communications of the ACM 24(6), 381–395 (1981)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Hebert, M., Vandapel, N.: Terrain classification techniques from ladar data for autonomous navigation. In: Collaborative Technology Alliances Conference (May 2003)Google Scholar
  6. 6.
    Nascimeto, S., Mirkin, B., Moura-Pires, F.: A Fuzzy Clustering Model of Data and Fuzzy C-means. In: S. Proc. 19th IEEE Int. Conf. Fuzzy Syst., vol. 1, p. 302 (2000)Google Scholar
  7. 7.
    Pal, N.R., Pal, K., Keller, J.M., Bezdek, J.C.: A possibilistic fuzzy c-means clustering algorithm. IEEE Trans. Fuzzy Syst. 13(4), 517–530 (2005)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Bailey, T.: Mobile Robot Localisation and Mapping in Extensive Outdoor Environments. Dissertation paper (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.Dept. of Intelligence Robot EngineeringUniversity of Science and TechnologyDeajeonKorea
  2. 2.Dept. of Applied Robot TechnologyKITECHSangrok-guKorea

Personalised recommendations