FUZZY REASONING METHOD WITH LEARNING FUNCTION FOR REAR-END COLLISION AVOIDANCE SYSTEM

Rear-end collision avoidance systems composed of typical in-vehicle sensors and special devices, such as CCD cameras, laser radar, and brake actuators, are being developed. The CCD camera is used for recognition of preceding vehicles and the laser radar is for measuring the distance headway. The system warns the driver of rear-end collision danger and breaks automatically in case of emergency. It is more effective for the collision avoidance warning to correspond to each driver's characteristics. Consequently, timing of the warning must be changed according to each driver. One approach to solve this issue is to use fuzzy reasoning theorem with learning function. The relations between collision danger and six factors (distance headway, relative velocity, relative acceleration, vehicle velocity, steering condition, weather condition) are modeled using fuzzy system. The model is obtained by use of simplified if-then type fuzzy reasoning, and learning functions of each driver's deceleration character are applied to the consequent parts. By this learning function, the feedback of each driver's characteristic to the control rules can be possible. The effectiveness of this method is evaluated by the experimental results and reported.

  • Supplemental Notes:
    • Five volumes of papers and one volume of abstracts comprise the published set of conference materials.
  • Corporate Authors:

    VERTIS

    TORANOMOM 34 MORI BUILDING 1-25-5
    TORANOMON, MINATOKU, TOKYO 105  Japan 
  • Authors:
    • Ito, T
    • Hiroshima, Y
    • Nishioka, K
  • Conference:
  • Publication Date: 1995-11

Language

  • English

Media Info

  • Pagination: p. 1175

Subject/Index Terms

Filing Info

  • Accession Number: 00722057
  • Record Type: Publication
  • Report/Paper Numbers: Volume 3
  • Files: TRIS
  • Created Date: Jun 26 1996 12:00AM