City Safety Event Classification using Machine Learning

Abstract

City safety technology aims to reduce vehicle collisions using activated warnings and braking based on automated detection of environmental threats. However, automatic detection of tentative collisions may differ from driver perception, leading to false positive activations. This work analyses vehicle on-board sensor suite in the event of City Safety activations and learns the optimal features responsible for activation classifications. From the 152 activation events, 8 second multivariate logs containing 316 signals are mined to achieve around 98% of ROC_AUC score in event classification. Thus, supervised and semi-supervised classifications significantly bridge the gap between automated and human perception for autonomous driving functionalities.