This content is not included in
your SAE MOBILUS subscription, or you are not logged in.
Probalistic and Fuzzy Methods for Sensor Validation and Fusion in Vehicle Guidance: a Comparison
Technical Paper
1997-25-0085
Sector:
Event:
ISATA 1997
Language:
English
Abstract
This paper compares methods to deal with uncertainty associated with longitudinal distance sensors in an Intelligent Vehicle Highway Systems (IVHS) based on two approaches~probabilistic and fuzzy~for sensor validation and sensor fusion. The probabilistic approach uses Kalman Filter-based techniques, with on-line adaptive learning of noise characteristics. The fuzzy approach uses a fuzzy time series predictor and non-symmetric validation regions in which sensors readings are assigned confidence values. Each sensor has its own dynamic validation curve which is shaped according to sensor characteristics, taking into account the range, external factors affecting the sensor, reliability of the sensor, etc. We investigate the performance of these methods as applied to follower vehicle guidance for platooning tasks in an IVHS in the presence of Gaussian and non-Gaussian noise.