The effect of vibrational energy distribution on the level of driver detection

Abstract

A laboratory-based experiment was conducted to measure the effect of vibrational energy distribution on human cognitive detection of road surface based on steering wheel vibration. The test stimuli used in the current study were ten steering wheel acceleration time histories of mid-sized European automobiles. The ten original steering wheel time histories were manipulated via digital Butterworth filters to eliminate four different frequency bands from the steering wheel vibration spectrum of within 20 to 60 Hz. The ensemble, composed of both the original and the manipulated time histories, was used to perform a laboratory-based detection. During the test, participants were asked to judge if the actuated acceleration stimulus transmitted came from the road surface shown on photographs featured on a board directly in front of the test bench and rate the confidence of their judgement on a five-point scale ((1) = very sure there was no signal-(5) = very sure there was a signal)). The findings suggest that the elimination of vibrational energy in the frequency band of 26.32 to 34.64 Hz can be highly detrimental to human cognitive detection of road surface types and compromise the steering wheel feedback the most. The elimination can lead to the correct detection of road surfaces.

On Training Road Surface Classifiers by Data Augmentation

“…However, during the last few years, the emergence of autonomous or semi-autonomous car technology has strongly increased the interest in on-board systems, which can perform real-time surface classification to aid the driving assistance systems of the car by automatic power-assisted steering. A variety of works have recently been reported in this very active research area [6][7][8][9][10][11][12][13][14][15][16][17]. Most of them propose machine learning approaches, where an automatic classifier is to be trained from labelled feature vectors derived from sensor signals.…”