Obstacle Detection and Mapping System

Published

August 1, 1998

Author(s)

H Tsai-Hong, Steven Legowik, M Nashman

Abstract

This paper discusses and evaluates an obstacle detection algorithm developed at NIST in support of the DEMO III Unmanned Ground Vehicle (UGV) program. The algorithm is a hybrid of grid-based and sensor-based obstacle detection and mapping techniques and is implemented as a module of the integrated 4D-Realtime Control System (RCS) system. The module consists of two sections: An obstacle detection section that processes range data read from a ladar sensor and uses this information to detect obstacles. A mapping section that projects obstacle points onto a grid-based representation map used to generate a traversable path for the vehicle.We describe the sensors used in the 4D-RCS autonomous driving system, the laser range finder (Ladar) sensor's characteristics, the obstacle detection algorithm, and the obstacle mapping procedure. We next evaluate the algorithm's performance on both man-made and natural obstacles. We have demonstrated autonomous driving with obstacle detection and avoidance on the NIST GROUNDS AND THE Nike site at speeds of up to 15 miles per hour.

Citation

NIST Interagency/Internal Report (NISTIR) - 6213

Report Number

6213

NIST Pub Series

NIST Interagency/Internal Report (NISTIR)

Pub Type

NIST Pubs

Download Paper

Local Download

Keywords

Vision, Mobility, Unmanned Systems, autonomous driving, image processing, LADAR, negative obstacles, obstacle detection

Citation

Tsai-Hong, H. , Legowik, S. and Nashman, M. (1998), Obstacle Detection and Mapping System, NIST Interagency/Internal Report (NISTIR), National Institute of Standards and Technology, Gaithersburg, MD, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=820625 (Accessed October 31, 2024)