Driving task identification method

• Main Authors: JIN LISHENG, YAN FUGANG, SHI JIAN, CHEN MEI, ZHU FEITING, FENG CHENGHAO, WANG YUHAN, WANG FANGRONG, XU PENGZHI, JIA SUHUA, GAO MING, SUN DONGXIAN, HUA QIANG, XIA HAIPENG, GUO BAICANG, WANG YAN
• Format: Patent
• Language: Chinese; English
• Published: 21.05.2019
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention relates to a driving task identification method, which comprises the following steps of: establishing a driving standard grade evaluation model by utilizing a driving standard evaluationindex, and selecting a driver with a high standard grade as a test object; designing a test object to execute a real vehicle test of several common driving tasks, and allocating a driving task digital recognition sequence to each driving task; establishing a driving task feature model based on the deep neural network by utilizing the driving task identification index and the driving task digitalidentification sequence; acquiring a driving task identification index of the tested driver, respectively inputting the driving task identification index into each driving task feature model, measuring and testing the significance difference between the driving task and each feature model by using the fitting goodness, and mapping the driving task feature model with the highest fitting goodness totest the driving task of t