In-car speed estimations with real, virtual, and no view

Car handling, and hence, safety, is affected by the way we estimate speed. Speed, however, is often underestimated in degraded visual environments, including virtual environments such as driving simulators. In simulators the visual and physical motion are typically incongruent as limited by quality and amplitude, respectively, which may cause a negative transfer of training. To improve the (training) quality of simulators and make them feel more real, it would be helpful to fill a knowledge gap on in-car speed perception as affected by real and virtual views, within a single group of subjects. We did so by testing whether estimations of speed in terms of km/h could be a valid metric for that purpose. We therefore exposed 17 subjects, seated as passengers in the front of a car on a straight road to four experimental conditions: (1) driving with a real out-the-window view, (2) driving with a live video view, (3) standing still watching pre-recorded video's, and (4) driving with eyes closed. Field-of-view was made equal in all conditions. Speeds tested ranged between 20 and 60 km/h. On average, speed was estimated 5 km/h less than actual, while we did not find a statistically significant difference between the four conditions tested. These results seem to contradict previous observations on motion perception, in particular in simulators, that have been ascribed to the quality of the visuals used. This finding may yet be explained by the assumption that speed estimations in terms of km/h are dominated by (conscious) cognitive processes, while visual-vestibular coherence between visual and physical motion, is dominated by (unconscious) sensorial driven perceptual processes. This disqualifies perceived speed as a valid metric for studying motion perception related to the optimisation of simulators.