Driving Behavior Control Based on an On-line Learning Algorithm

A driver steering control was modeled by using an idea of target position. The proposed model dealt with the driver decision-making mechanisms in tracking a target position by means of Neuro-Fuzzy system. Here, a cubic B-spline curve was employed to generate more flexible paths of lane- change to a target position. Additionally, a learning algorithm, utilizing local linear networks in the corresponding fuzzy areas to approximate the nonlinear function, was proposed to emulate a driver self-learning skills from his driving experience. Results from the simulation of the obstacle avoidance showed the capability of the proposed model to carry out a driver steering behavior with emphasis on learned skills.