Obstacle detection for robot navigation using structured light
Author(s)
Tran, Deborah L. (Deborah Lynn Hong), 1978-
DownloadFull printable version (8.903Mb)
Other Contributors
Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science.
Advisor
Kenneth M. Houston and Leslie Pack Kaelbling.
Terms of use
Metadata
Show full item recordAbstract
Obstacle detection is an essential function for autonomous mobile robots. Current autonomous systems are generally heavy, high-powered devices. Additionally, obstacle detection systems often employ active ranging sensors that exhibit poor angular resolution, thereby preventing vehicles from navigating through narrow spaces. Other systems require considerable processing to resolve objects. The work in this thesis attempts to design a small, lightweight, low-cost, and low-power system to detect obstacles in the direct field of view of a small robotic vehicle. In particular, the range to the obstacle as well as shape estimation is key data that would aid in robot navigation as well as data gathering. Rather than using conventional active or passive ranging techniques, this thesis examines projections of structured light to determine range to the obstacle and surface information of the obstruction. A physical model was developed and tested through simulation, and verified in hardware.
Description
Thesis (M.Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2001. Includes bibliographical references (p. 84-85).
Date issued
2001Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer SciencePublisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.