Driver Performance Model (DPM) development has provided results reflecting on the debate between on-road and driving-simulator data in driving research. Developed for the Federal Highway Administration, DPM is a computational microprocess model of driver behavior that has been designed to simulate--in detail--the driver's perceptual, cognitive, and control processes to generate steering, braking, and acceleration inputs to the vehicle. The requirement to develop driver data for prediction of absolute on-road performance--versus typical interest in ordinal findings to be later validated via on-road studies--led to the collection of comparable on-road and simulator data and their subsequent comparison. Comparisons of corresponding curve-entry speeds and speed profiles revealed a profound divergence between the on-road and simulator results (t = 9.39, p < .005). Compared with simulator drivers, on-road drivers tended to have higher curve-entry speeds for the more difficult (sharper) curves and lower speeds for the less difficult curves. This trend, though reduced in magnitude, was apparent even after statistical adjustments for differences in respective tangent speeds (t = 2.67, p < .01). These results are discussed in light of emerging on-road and simulator capabilities. The discussion and earlier results altogether supported two conclusions: (a) debate concerning on-road versus simulator research studies is likely to continue with their rapidly emerging individual capabilities, and (b) on-road research currently provides the best basis for driver model development where one-to-one real-world predictions are required (e.g., DPM).
Abstract