Calculation and Validation of Driver’s Readiness for Regaining Control from Autonomous Driving

Abstract

In level 3 automated driving, if the vehicle fails to drive automatically or the operational design domain (ODD) ends, the human driver must control the vehicle i.e., be a fallback-ready user. So far, human drivers have had little experience of taking over vehicle control during driving and there is a lack of research on how they react in this situation. Consequently, there has been a research need to know how much the driver is ready to take-over the control authority, in order to predict and compensate the risk of the transition to manual driving from the out of the control loop. In this paper, we propose the concept of the driver’s readiness (DR). To calculate the DR, we propose to use various human factors, such as workload, situation awareness, attention, activeness and so on. In order to validate our proposed algorithm, the heuristic experiments have been performed. We have drawn our real-time DR calculation algorithm and validated with subjective observations from 30 participants. The results of regression analysis show that the subjective observations and DR calculations have linear relationships.