Man-machine co-driving test method based on digital twin virtual-real interaction technology

Abstract

The invention discloses a man-machine co-driving test method based on a digital twin virtual-real interaction technology. The method comprises the steps: transmitting virtual simulation scene information detected by a virtual sensor to an automatic driving controller in a real vehicle through a 5G communication base station through a virtual simulation scene and a virtual sensor (a radar, a camera and the like); using an automatic driving controller of a real vehicle to judge driving operation needing to be executed by the vehicle in a current scene and generating interaction and takeover information or early warning information with a driver; meanwhile, using the automatic driving controller of the real vehicle to receive a control instruction from a driver in a driving simulation cabin and driver behavior information transmitted by a driver behavior monitoring module to judge the driving state of the driver and determine a human-vehicle co-driving weight factor; and meanwhile, collecting operation and interaction information of the driver on the vehicle so that the man-machine interaction and co-driving performance of the vehicle and the comfort of passengers can be fully tested and optimized subsequently.

Description

technical field [0001] The invention relates to the field of human-machine co-driving testing, in particular to a human-machine co-driving testing method based on digital twin virtual-real interaction technology. Background technique [0002] According to the different degrees of automation of smart cars, the Society of Automotive Engineers divides smart cars into manual driving, driving assistance, partial automation, conditional automation, high automation and full automation, corresponding to L 0 -L 5 These six autonomous driving levels. According to the definition of each level, L 0 -L 2 During the driving process of these three autonomous driving levels, the driver still plays a dominant role in vehicle control, and the vehicle only plays the role of assisting the driver in operation. L 3 Level smart cars have preliminarily possessed the ability of independent judgment and decision-making. When the vehicle meets certain conditions, it can perform automatic driving,...

AI Technical Summary

Problems solved by technology

Although this test method greatly saves time and economic cost, and avoids the risk caused by the failure of the driver's real vehicle test, but because the whole test adopts virtual simulation or some modules are replaced by hardware, so Its test conditions, test scenarios, human-computer interaction and driving experience are quite different from real vehicles and traffic scenarios.

In addition, human-machine control switching often occurs when the vehicle is in an emergency and the vehicle cannot handle the current driving scene. Therefore, if the driver's real vehicle test is directly used, it will inevitably bring greater test risks.

Images