Lane change path planning in emergency situation based on skilled driver's Performance

Lane Change at high speeds, where there are chances of incidents, is a strategic maneuver to avoid collision. In this situation, due to the limited time for doing maneuver, decision speed and path planning are of critical importance. In this paper, based on a skilled driver’s performance in a similar situation, a proper path and corresponding appropriate control system was designed with the aim of vehicle stability preservance and collision avoidance. To fulfill this purpose, possible paths were identified using the vehicle dynamic model and driver’s Performance type and a neural network system was trained to determine the range of the feasible path focused on maintaining the vehicle stability constraints and to generate the trajectory. A hybrid controller is hired for the vehicle navigation which consists of the driver's performance pattern with a covering neural network along with two PD controllers. Carsim along with Simulink-MATLAB software were used to verify the control system designed in presence of the uncertainty conditions of road friction coefficient in both dry and wet road modes. The results show that the controller was able to steer the car at different speed and road conditions, flawlessly. The Novelty of this method are the simultaneous design of a stable path, while maintaining geometric constraints and the low computational burden of the path planning and control system, in the emergency situations.