CAPTURING AND MODELING OF DRIVING SKILLS UNDER A THREE DIMENSIONAL VIRTUAL REALITY SYSTEM BASED ON PWPS

This paper develops a new framework to aid the understanding of driving maneuvers based on the expression as HDS focusing on the driver's stopping maneuver. Driving data was collected by using a 3-D driving simulator based on CAVE, which provides 3-D visual information. In the authors' modeling, the relationship between the measured information, such as distance to the stop line, its 1st and 2nd derivatives, and the braking amount is expressed by the PWPS model, which is a class of HDS. The key to solve the identification problem was to formulate the problem as the MILP with replacing the switching conditions by binary variables. From obtained results, it was found that the driver appropriately switches the control law according to the following scenario: at the beginning of the stopping behavior, the driver decelerates the vehicle based on acceleration information, and then switches to the control law based on the distance to the stop line.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/0780379063
• Corporate Authors:

  Institute of Electrical and Electronics Engineers (IEEE)

  3 Park Avenue, 17th Floor
  New York, NY  United States  10016-5997
• Authors:
  • Kim, J-H
  • Hayakawa, S
  • Suzuki, T
  • Hirana, K
  • Matsui, Y
  • Okuma, S
  • Tsuchida, N
• Conference:
  • 29th Annual Conference of the IEEE Industrial Electronics Society
  • Location: Roanoke, Virginia
  • Date: 2003-11-2 to 2003-11-6
• Publication Date: 2003

Language

• English

Media Info

• Features: References;
• Pagination: p. 818-823
• Serial:
  • Volume: 2

Subject/Index Terms

• TRT Terms: Automobile driving; Driving simulators; Highway safety; Human factors; Traffic control; Traffic models; Traffic simulation; Virtual reality
• Subject Areas: Highways; Operations and Traffic Management; Safety and Human Factors; I73: Traffic Control;

Filing Info

• Accession Number: 00979098
• Record Type: Publication
• ISBN: 0780379063
• Files: TRIS
• Created Date: Sep 15 2004 12:00AM