A Path Planning Method Based on Large Amount of Artificial Driving Trajectories 2018-01-1588

In recent years, autonomous vehicles have become the focus of research, among them, path planning is one of the key points. How to plan a trajectory in line with human driving habits in a complex traffic scenario is a concern of automatic driving agencies. Only if the trajectory closer to the driving habits of humankind, will people sitting in the car feel more stable and comfortable and there is no sense of difference with their own driving. To achieve this, this paper presents a method based on large amount of artificial driving trajectory generation planning path, combined with high-precision map and manual driving trajectory, through the road segment, standardization of road segments and building cell path sets, to obtain the optimal path. As the planning experiment of at the end of this paper shows, the results of our routing experiment at the roundabout show the effectiveness of our method.