Vehicle driving behavior predicating method based on machine learning

Abstract

A vehicle driving behavior predicating method based on machine learning relates to the field of Internet-of-vehicles. The invention aims to utilize machine learning technology for mining a relation among vehicle attribute, road information, driving environment information and a vehicle driving behavior, thereby improving accuracy in predicating the vehicle driving behavior. The method comprises the following steps of 1, defining a characteristic set: defining a vehicle characteristic, defining a road characteristic and defining a vehicle driving environment; 2, operating a vehicle displacementpredicating model, performing characteristic extraction and data preprocessing, extracting a distance characteristic between the vehicle and a front crossing, extracting a crossing allowed turning action characteristic, and extracting a label; operating a vehicle displacement predicating model, defining a training sample set, and training the vehicle displacement predicating model; 3, operating avehicle driving behavior predicating model, and defining a Gaussian component; and 4, predicating the vehicle driving behavior.

Description

technical field [0001] The invention relates to the field of Internet of Vehicles, in particular to a method for predicting vehicle driving behavior based on machine learning. Background technique [0002] Vehicle driving behavior prediction mainly serves applications related to the safety of the Internet of Vehicles, such as vehicle anti-collision monitoring at intersections. The existing research on vehicle driving behavior prediction mainly considers the historical behavior trajectory of the vehicle and the road condition information of the vehicle. These studies idealize the modeling of vehicles and road conditions, ignoring the vehicle's own attributes (such as body length and width), the distance from the vehicle to the intersection, traffic signals and lane turning permission signs and other important factors that affect vehicle driving behavior, resulting in There is a large deviation between the prediction results of driving behavior on real urban roads and the act...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem that the existing vehicle driving behavior prediction model is insufficient in mining the relationship between vehicle body attributes, road information, and driving environment and driving behavior, the pre...

Images