Bringing a Vehicle to a Controlled Stop: Effectiveness of a Dual-Control Scheme for Identifying Driver Drowsiness and Preventing Lane Departures Under Partial Driving Automation Requiring Hands-on-Wheel

Partial driving automation systems execute sustained lateral and longitudinal control, while humans are required to supervise the automated features. Similar with drivers using manual settings, those may also experience drowsiness. However, existing that aim detect driver drowsiness tend be unreliable. This study applies a dual-control scheme in partial context which must keep their hands on vehicle’s steering wheel. executes control when vehicle lane departure is anticipated (because of inappropriate torque input), then, activates deceleration if does not properly perform action. To determine whether supervising automation, attempts create an opportunity for driver–automation interactions. Thus, controller’s objectives twofold: safety state identification. investigated effectiveness identifying preventing departures only information. Twenty participated fixed-base simulator experiment sleep-inducing environment. While we observed cases system could effectively bring controlled stop, timeliness accuracy identification remained as issues owing indirect links between drivers’ level controller activation. We conclude although useful mechanism avoid departures, needs improved ensure timely effective detection