Obstacle Avoidance On The Autonomous Land Vehicle Using The Warp Systolic Array Machine

R. Terry Dunlay

doi:10.1117/12.968235

1 January 1987 Obstacle Avoidance On The Autonomous Land Vehicle Using The Warp Systolic Array Machine

R. Terry Dunlay

Proceedings Volume 0852, Mobile Robots II; (1987) https://doi.org/10.1117/12.968235
Event: Advances in Intelligent Robotics Systems, 1987, Cambridge, CA, United States

Abstract

This paper describes range image based obstacle avoidance methods developed to run on the Warp Machine, a new linear systolic array processor capable of delivering up to 100 million floating point operations per second. The Warp processing described here has been tested on the DARPA Autonomous Land Vehicle (ALV) to detect and locate obstacles present in an outdoor road environment at speeds up to 10 km/hour. The overall perception system consists of two subsystems; a color image processing subsystem used to find the road area and the Warp based range image processing subsystem. We briefly describe the architecture of the Warp Machine and methods of exploiting the parallelism of the Warp system. Next we describe the details of the obstacle avoidance perception algorithm and its mapping onto the Warp Machine. Results of applying the system in an experimental test run are presented.

Citation Download Citation

R. Terry Dunlay "Obstacle Avoidance On The Autonomous Land Vehicle Using The Warp Systolic Array Machine", Proc. SPIE 0852, Mobile Robots II, (1 January 1987); https://doi.org/10.1117/12.968235

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available