ABSTRACT
This study, proposes a comprehensive strategy for automatic emergency lane change. The system is designed to take control of the vehicle immediately after driver drowsiness is detected. The system is able to guide the vehicle in a dynamic traffic environment and take it safely to the far right side of the road based on the orders received from the decision-making and path-planning units. In this approach first, a reliable driver drowsiness detection system is developed which applies a combination of an image processing-based technique as well as a method based on driver-vehicle interaction. Then, a novel algorithm for decision-making on autonomous lane change maneuver is investigated. The proposed approach can dense a number of constraints, based on the vehicle’s dynamics and environmental conditions, which must be satisfied for a safe and comfortable lane change maneuver. Afterwards, a path-planning system is developed which applies a fifth order polynomial function as the path equation. The coefficients and parameters of the path function are interrelated based on the physical characteristics of the problem. Finally, a fuzzy-LQR controller is designed which guides the vehicle through the designed path.
