Study of quantification method of driving behavior characteristics using risk potential

Abstract

In the risk potential driver model used to generate path control targets for autonomous vehicles, traffic elements such as obstacles and traffic rules are represented by risk potential, and safe routes are determined by synthesizing them. Therefore, it is possible to calculate the control target path adapted to the individual by quantifying the feel of risk that the human driver perceives and using it as a parameter of the driver model. The cognitive characteristics of the risk in the traffic scene are different for each driver. This paper describes a method for estimating risk potential parameters using a driving action with unevenness. At first, the risk potential parameter to receive from surrounding obstacles was estimated using the data of the travelling trajectory. The characteristic of the driving behavior of the human driver was expressed as random variable for the accumulation data of a risk potential parameter. By calculating a risk potential parameter, and accumulating as data, it was suggested that the risk feel that each driver received from the surrounding was quantified.