The PhD thesis is composed of two different but related parts. The first part deals with the development of an intelligent system for driver drowsiness detection. The system proposes a new algorithm based on the combination of several different detection methods. Hence, an image processing-based technique as well as a method based on driver-vehicle interaction will be used. A driving simulator will be used to gather real data and then artificial neural networks are going to be used in the structure of the designed system.
In the second part, a novel algorithm for lane change maneuver will be studied. The control unit must be able to perform a lane change maneuver in a dynamic environment in order to guide vehicle from speed lane to the most right lane of the road. Hence, the control unit should be composed of three different layers. In the first layer, the feasibility of a lane change maneuver should be decided (decision making layer), then, a desired trajectory should be planned in the second layer (path planning unit), and finally, the vehicle should be leaded to take the desired path (lane tracking unit).