Driver Behavior Classification under Cut-In Scenarios Using Support Vector Machine Based on Naturalistic Driving Data

Cut-in scenario is common in traffic and has potential collision risk. Human driver can detect other vehicle’s cut-in intention and take appropriate maneuvers to reduce collision risk. However, autonomous driving systems don’t have as good performance as human driver. Hence a deeper understanding on driving behavior is necessary. How to make decisions like human driver is an important problem for automated vehicles. In this paper, a method is proposed to classify the dangerous cut-in situations and normal ones. Dangerous cases were extracted automatically from naturalistic driving database using specific detection criteria. Among those cases, 70 valid dangerous cut-in cases were selected manually. The largest deceleration of subject vehicle is over 4 m/s². Besides, 249 normal cut-in cases were extracted by going through video data of 2000km traveled distance. In normal driving cases, subject vehicle may brake or keep accelerating and the largest deceleration was less than 3 m/s². The time when driver initiated to brake was defined as key time. But if driver had no brake maneuver (it happened in normal driving), the time when cutting-in vehicle’s front wheel crossing line was defined as key time. All the factors values discussed referred to the values of key time. Longitudinal safety was related to THW (Time Headway) and relative velocity. Support Vector Machine (SVM) was utilized to classified dangerous cut-in situations and normal ones. The accuracy of SVM model was 89.97%. Scatter diagram was plotted on THW-relative velocity plane and this plane could be divided into dangerous zone and normal zone. The classification method in this paper can provide theory evidence for Advanced Driver Assistance Systems (ADAS) control strategy to make the systems tackle cut-in in a more human-like way and facilitate evaluation of automated vehicle.