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

• Main Authors: PENG BINBIN, ZHU JUNWEI, HE DEFENG, SONG XIULAN, YU SHIMING, ZHENG YAYU
• Format: Patent
• Language: Chinese; English
• Published: 05.07.2019
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

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 c