DriverSense: a hyper-realistic testbed for the design and evaluation of novel user interfaces in self-driving vehicles

This paper presents DriverSense, a novel experimental platform for designing and validating onboard user interfaces for self-driving and remotely controlled vehicles. Most of currently existing academic and industrial testbeds and vehicular simulators are designed to reproduce with high fidelity the ergonomic aspects associated with the driving experience. However, with increasing deployment of self-driving and remote controlled vehicular modalities, it is expected that the digital components of the driving experience will become more and more relevant, because users will be less engaged in the actual driving tasks and more involved with oversight activities. In this respect, high visual testbed fidelity becomes an important pre-requisite for supporting the design and evaluation of future onboard interfaces. DriverSense, which is based on the hyper-realistic video game GTA V, has been developed to satisfy this need. To showcase its experimental flexibility, a set of selected case studies, including Heads-Up Diplays (HUDs), Augmented Reality (ARs) and directional audio solutions, are presented.