Intelligent network connection vehicle preceding vehicle acceleration prediction method based on Gaussian process regression

Abstract

The invention discloses an intelligent network connection vehicle preceding vehicle acceleration prediction method based on Gaussian process regression. The method comprises: selecting data of n historical moments at the current moment as input of a training set, the accelerations at n historical moments of the preceding vehicle measured at the current moment are taken as the output of a trainingset; predicting preceding vehicle accelerations at n future moments through Gaussian process regression; then, an iteration method is utilized; at the next moment, the acceleration values of n new historical moments of the preceding vehicle are measured again, the preceding vehicle acceleration of n new moments in the future is predicted through Gaussian process regression, the first prediction value is taken as the prediction reference value of the next moment, and the steps are repeated so that the value of the preceding vehicle acceleration can be predicted online, and the prediction deviation can be continuously corrected. The method is less in parameter setting, simple in design, easy to understand, simple and convenient to implement online and high in practicability, the prediction deviation can be continuously corrected while the acceleration value of the preceding vehicle is predicted online, and the problem that the acceleration of the preceding vehicle is difficult to predictis solved.

Description

technical field [0001] The invention belongs to the field of automatic control of intelligent networked vehicles, and relates to a method for predicting the acceleration of a front vehicle of an intelligent networked vehicle based on Gaussian process regression. Background technique [0002] In recent years, the number of vehicles on urban roads has increased rapidly, and the problems of energy consumption and environmental pollution have become increasingly serious. In the process of following a car on urban roads, it is inevitable that the vehicle in front will continue to accelerate and decelerate. If the vehicle can predict the acceleration change of the vehicle in front well, it can make preparations for acceleration and deceleration in advance, so that the vehicle The changes in acceleration and deceleration are smoother, reducing fuel consumption and providing better comfort for passengers and drivers. Since the acceleration of the front vehicle is uncontrollable, it...

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the lack of prediction of the acceleration of the front vehicle in the prior art, the present invention provides a method for predicting the acceleration of the front vehicle of an intelligent networked vehicle based on Gaussian process regression, which is intuitive to understand, simple in design, and strong in adaptability. Dealing with the unpredictable acceleration of the front vehicle

Images