Nowadays Autonomous vehicles are emerging into market. These vehicles use special OBD system i.e. On Board Diagnosis system.
In terms of driving behavior modeling algorithms, there are
HMM, support vector machine (SVM), decision trees, and
other principles. The main application of the driving behavior
analysis is the identification of driving lethargy or the driver’s
actions forecast. In this paper, a novel driving behavior
analysis method based on the vehicle OBD and AdaBoost
algorithms is proposed. This proposed method collects the
vehicle operation information, including vehicle speed,
engine RPM, throttle position, and calculated engine load, from the OBD interface. Then the proposed method makes
use of AdaBoost algorithms to create a driving behavior
classification model, and finally could determine whether the
current driving behavior belongs to safe driving or not.
Experimental results show the correctness of the proposed
driving behavior analysis method can achieve average of
99.8% accuracy rate in various driving simulations.
1 Like