Automatic Maneuver Recognition in the Automobile: the Fusion of Uncertain Sensor Values using Bayesian Models
Arati Gerdes · elib (German Aerospace Center) · 2006
A probabilistic system for automatic driving maneuver recognition from CAN-Bus and sensor data is in development at the German Aerospace Center (DLR). Major obstacles to automatic maneuver recognition in the automobile today are presented by the wide variety of styles in which driving maneuvers are performed and the high degree of uncertainty present in the sensor data. Traditional rule-based systems are ill-equipped to deal with these problems. Instead, Bayesian models, which offer a solid, theoretical framework for the derivation of inferences from uncertain evidence, are used for the inference of the driving maneuver being performed. Driver behavior analysis and tests of a prototype maneuver-recognition system are performed in real traffic using the ViewCar, a research vehicle equipped with cameras and sensors to measure and record CAN-Bus, environment and driver data. Experiments with the prototype system yield a driving maneuver recognition rate of approximately 92%.