The 20th and 21st joint COTA International Conference of Transportation Professionals (CICTP 2020-21)

Detecting whether the driver's hand is off the steering wheel in time and warning the driver can improve the driving safety. However, due to the impact of the vehicle’s movement and the significant variation across different driving environment, detecting the position of the driver’s hand is challenging.This paper presents a method of using sensor data of smartwatch and smartphone to detect whether the driver's hand is on the steering wheel in real time. This method infers whether the driver's hand is on the steering wheel based on the gravity signal and the vibration signal and whether the vehicle is turning. In addition，this paper employs a method which keeps updating the training dataset to adapt to dynamic changdes during driving. The evaluation of actual driving scenarios shows that this method can achieve a detection accuracy of about 90%.

CICTP