Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
I n t e l l i m o t i o n p a g e 6 v o l u m e 5 n u m b e r 2 1 9 9 6
 

Summary: I n t e l l i m o t i o n p a g e 6
v o l u m e 5 n u m b e r 2 1 9 9 6
Intelligent Sensor
N
o sensor will deliver accurate information
at all times. Many uncertain influences
may add noise to sensor readings, or cause
a total malfunction of the sensor. To avert these
effects, and to maintain the high level of safety that
is an integral part of intelligent transportation sys-
tems, we propose a fault tolerant supervisory con-
trol architecture. It consists of five main modules:
sensor validation, sensor fusion, fault diagnosis, haz-
ard analysis, and a safety decision maker.
Two methods have been identified and developed
for these modules. One is based on probability
theory, the other on fuzzy logic. The probability
approach models the sensors, along with potential
failures, as probabilistic events and adaptively esti-
mates the probabilities of these events on-line. For

  

Source: Agogino, Alice M. - Department of Mechanical Engineering, University of California at Berkeley

 

Collections: Engineering