NAVIGATION CONTROL FOR AN AUTONOMOUS ROAD VEHICLE USING NEURAL NETWORK

This paper describes an autonomous navigation method for road vehicles using an artificial neural network based on competitive learning. The input of the network consists of visual information obtained from a CCD camera and vehicle speed, and the output is steering angle to keep the vehicle at the center of the lane. In the experiment, the control system takes over handling steering from a human driver just after observing the person drive. The performance level is comparable to that of a normal human driver and the authors' autonomous vehicle runs on Seoul-Pusan Expressway at 80-120 km/hr speed at daytime, night time, as well as in rainy weather.

• Supplemental Notes:
  • Full conference proceedings available only on CD.
• Corporate Authors:

  ITS America

  1100 17th Street, NW, 12th Floor
  Washington, DC  United States  20036
• Authors:
  • Moon, S-H
  • Kim, C-W
  • Han, M-H
• Conference:
  • Intelligent Transportation: Realizing the Future. Abstracts of the Third World Congress on Intelligent Transport Systems
  • Location: Orlando, Florida
  • Date: 1996-10-14 to 1996-10-18
• Publication Date: 1996

Language

• English

Media Info

• Pagination: n.p.

Subject/Index Terms

• TRT Terms: Advanced vehicle control systems; Artificial intelligence; Neural networks; Steering
• Old TRIS Terms: Autonomous vehicle navigation
• Subject Areas: Highways; Operations and Traffic Management; Vehicles and Equipment; I95: Vehicle Inspection;

Filing Info

• Accession Number: 00741786
• Record Type: Publication
• Files: TRIS
• Created Date: Oct 28 1997 12:00AM