Abstract

More and more Advanced Driver Assistance Systems (ADASs) are entering the market for improving both safety and comfort. Adaptive Cruise Control (ACC) is an ADAS application that has high interaction with the driver. ACC systems use limited sensor input and have only few configuration possibilities. This may result in the behaviour of the ACC not matching user's preferences in all cases, resulting in lower acceptance of the system. In this work, we examine the possibilities for a Personalised ACC (PACC), which adapts the ACC settings such that it matches the driver preference in order to increase the acceptance. The driver preferred ACC behaviour is predicted using machine learning techniques and manual driving data. On-road experiments showed that the method is promising as it is able to discriminate between two preference clusters with an accuracy of 85%.

Abstract

The number of fatal car-cyclist accidents is increasing. Advanced Driver Assistance Systems (ADAS) can improve the safety of cyclists, but they need to be tested with realistic safety-critical car-cyclist scenarios. In order to store only relevant scenarios, an online classification algorithm is needed. We demonstrate that machine learning techniques can be used to detect and classify those scenarios based on their trajectory data. A dataset consisting of 99 realistic car-cyclist scenarios is gathered using an instrumented vehicle. We achieved a classification accuracy of the gathered data of 87.9%. The execution time of only 45.8 us shows that the algorithm is suitable for online purposes. cop. 2015 IEEE.