Simulations and Self-Driving Cars: A Study of Trust and Consequences

Trust plays an essential role in ensuring safe and robust human-robot interaction. Recent work suggests that people can be too trusting of technology, leading to potential dangerous situations. We carried out a series of experiments in an autonomous car simulator, in order to test if there is a difference in peoples behavior when real-life consequences are applied, compared to pure simulation. The study was carried out with six experimental conditions in a between-subject design in which participants (N = 121) interacted with the simulator and were told they could assume control of the autonomous car at any point during the simulation. Results show that participants are significantly less trusting of the autonomous system, when real-life consequences were involved (p = .014).