Vehicle Automation Field Test: Impact on Driver Behavior and Trust

Abstract

With the growing technological advances in autonomous driving, the transport industry and research community seek to determine the impact that autonomous vehicles (AV) will have on consumers, as well as identify the different factors that will influence their use. Most of the research performed so far relies on laboratory-controlled conditions using driving simulators, as they offer a safe environment for testing advanced driving assistance systems (ADAS). In this study we analyze the behavior of drivers that are placed in control of an automated vehicle in a real life driving environment. The vehicle is equipped with advanced autonomy, making driver control of the vehicle unnecessary in many scenarios, although a driver take over is possible and sometimes required. In doing so, we aim to determine the impact of such a system on the driver and their driving performance. To this end road users' behavior from naturalistic driving data is analyzed focusing on awareness and diagnosis of the road situation. Results showed that the road features determined the level of visual attention and trust in the automation. They also showed that the activities performed during the automation affected the reaction time to take over the control of the vehicle.

Real-World Evaluation of the Impact of Automated Driving System Technology on Driver Gaze Behavior, Reaction Time and Trust

“…Other studies that reported the take over reaction time (TOrt) in different scenarios showed that TOrt stayed fairly consistent, between 2 and 3.5 seconds [23]. However, experiments performed under real driving conditions showed that drivers needed less than one second to take back the control of the vehicle, this time varying depending on the road conditions and tasks performed [15].…”

“…This is the case, for example, in curvy roads driven at high speed [14]. Several studies have investigated driver reactions in this scenario, the work in [15] showing that the road features affect the driver's level of visual attention and trust in the automation. Additional research indicated that the existence of curves increased lateral acceleration and reaction time to respond to a TOR [16].…”

“…Another important factor that affects the process of regaining control of the vehicle is the performance of NDRT [15], [13], [19], [20], [21]. Furthermore, tasks that involve a high cognitive load [13] increase driver reaction time to a TOR compared to low cognitive load tasks.…”

“…Studies that assess driver response to TOR in real road scenarios are very scarce. In this work we build on the research presented in [15], in which experiments were conducted in a real life driving scenario and thereby contribute to the scientific community by investigating the impact of automation on driver behavior under several speed and NDRT conditions that have not been previously considered in real driving conditions.…”

Chair for Intelligent Transportation Systems–Sustainable Transport Logistics 4.0

“…For example, during conditional automation, a timely response from a driver during a take-over request in the event of an unexpected situation is crucial to ensure road safety. To this end, the effect of nondriving tasks in a real-world environment is assessed, taking into account a driver's state and the environment [4], [5].…”