Design and Implementation of a Hybrid Path Planning Approach for Autonomous Lane Change Manoeuvre

Autonomous vehicles are currently on their way and they have already started to gradually alter the fundamentals of the entire transport system. However, while in relatively near future, seeking to use their full potential during various urban traffic scenarios, further developments must be done in such fields as the sensing and perception, path planning and control. This research work focuses on the path planning problems and proposes a novel hybrid path planning approach, specifically designed for an important and complex urban scenario—the lane change manoeuvre. The proposed hybrid path planner consists of two classical path planning approaches: the Bézier curves approach, which served as a primary planner, and the rapidly exploring random trees approach, which was used as a supplementary planner. The entire development process of the hybrid path planner is described systematically and in detail. To verify the efficiency of the proposed hybrid path planner, experimental test drives, while using an autonomous research vehicle, were performed. The experimental results indicated that the real-time performance of the proposed hybrid path planning approach is effective and reliable. The path generated by the proposed hybrid approach is feasible, continuous, and can be executed by the autonomous vehicle.