A Gaussian Process Regression Based Acceleration Prediction Method for Front Vehicles of Intelligent Connected Vehicles

A technology of Gaussian process regression and prediction method, which is applied in the field of acceleration prediction of intelligent networked vehicles based on Gaussian process regression. , the effect of less method parameters

Active Publication Date: 2022-03-01
ZHEJIANG UNIV OF TECH
View PDF15 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Gaussian Process Regression Based Acceleration Prediction Method for Front Vehicles of Intelligent Connected Vehicles
  • A Gaussian Process Regression Based Acceleration Prediction Method for Front Vehicles of Intelligent Connected Vehicles
  • A Gaussian Process Regression Based Acceleration Prediction Method for Front Vehicles of Intelligent Connected Vehicles

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The method of the present invention will be described in further detail below in conjunction with the accompanying drawings.

[0044] refer to figure 1 and figure 2 , a method for predicting the acceleration of a front vehicle based on a Gaussian process regression, the method comprising the steps of:

[0045] 1) Select the training set sample, and measure the acceleration data a(t-10), a(t-9),...,a(t-1) of the vehicle in front at 10 (n takes 10) historical moments at time t, so that time x i =t-11+i, acceleration sample value y i =a(t-11+i), i=1,2,...,10, let X={x 1 ,x 2 ,...,x i} is expressed as 10 historical moments at the current moment t, Y={y 1 ,y 2 ,...,y i} is expressed as the acceleration data of the vehicle in front at 10 historical moments measured at the current moment t; X is used as the input of the training set, and Y is used as the output of the training set, where Y obeys the Gaussian distribution, see formula (1):

[0046] Y=F(X,X)~N(M(X,X),K(...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

A method for predicting the acceleration of the front vehicle of an intelligent networked vehicle based on Gaussian process regression. The data of n historical moments at the current moment are selected as the input of the training set, and the acceleration of the previous vehicle at n moments of history measured at the current moment is used as the training The output of the set is to predict the acceleration of the front vehicle at n moments in the future through Gaussian process regression, and then use the iterative method to re-measure the acceleration value of the new historical n moments of the front vehicle at the next moment, and predict it through Gaussian process regression For the acceleration of the front vehicle at n times in the future, the first one of the predicted value is taken as the prediction reference value at the next moment. Repeating this cycle, the online prediction of the acceleration of the front vehicle can be realized, and the prediction deviation can be continuously corrected. The method of the invention has few parameter settings, simple design, easy understanding, simple on-line implementation and strong practicability, can realize on-line prediction of the acceleration value of the front vehicle and continuously correct the prediction deviation, and solves the problem that the acceleration of the front vehicle is difficult to predict.

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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06Q10/04G06F30/20
CPCG06Q10/04G06F30/20G06F18/214
Inventor 何德峰彭彬彬余世明宋秀兰郑雅羽朱俊威
Owner ZHEJIANG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products