Carnegie Mellon University
The
Evaluation and Comparison of Terrain Classification Techniques from LADAR Data for Autonomous Navigation

Martial Hebert , Nicolas Vandapel, Stefan Keller, and Raghavendra Rao Donamukkala
23rd Army Science Conference, December, 2002.


Abstract
Autonomous navigation remains a considerable challenge, primarily because of the difficulty in describing the environment of the robot in a way that captures the variability of natural environments. In this paper, we focus on the problem of extracting the ground terrain surface from sparse 3-D data from LADAR mobility sensors, including the segmentation of the terrain from obscuring vegetation. We summarize three approaches to LADAR processing and discuss their limitations. Experimental evaluation was conducted with a GDRS LADAR sensor and with a Z+F laser range finder.

Keywords
vegetation, mobile robot, autonomous navigation

Notes
Associated Center(s) / Consortia: Vision and Autonomous Systems Center and Field Robotics Center
Associated Lab(s) / Group(s): 3D Computer Vision Group
Associated Project(s): CTA Robotics

Text Reference
Martial Hebert , Nicolas Vandapel, Stefan Keller, and Raghavendra Rao Donamukkala, "Evaluation and Comparison of Terrain Classification Techniques from LADAR Data for Autonomous Navigation," 23rd Army Science Conference, December, 2002.

BibTeX Reference
@inproceedings{Hebert__2002_4108,
   author = "Martial {Hebert } and Nicolas Vandapel and Stefan Keller and Raghavendra Rao Donamukkala",
   title = "Evaluation and Comparison of Terrain Classification Techniques from LADAR Data for Autonomous Navigation",
   booktitle = "23rd Army Science Conference",
   month = "December",
   year = "2002",
}