Recognition of Lane Changing Maneuvers for Vehicle Driving Safety

Abstract

The increasing number of vehicles has caused traffic conditions to become increasingly complicated in terms of safety. Emerging autonomous vehicles (AVs) have the potential to significantly reduce crashes. The advanced driver assistance system (ADAS) has received widespread attention. Lane keeping and lane changing are two basic driving maneuvers on highways. It is very important for ADAS technology to identify them effectively. The lane changing maneuver recognition has been used to study traffic safety for many years. Different models have been proposed. With the development of technology, machine learning has been introduced in this field with effective results. However, models which require a lot of physical data as input and unaffordable sensors lead to the high cost of AV platforms. This impedes the development of AVs. This study proposes a model of lane changing maneuver recognition based on a distinct set of physical data. The driving scenario from the natural vehicle trajectory dataset (i.e., HighD) is used for machine learning. Acceleration and velocity are extracted and labeled as physical data. The normalized features are then input into the k-nearest neighbor (KNN) classification model. The trained model was applied to another set of data and received good results. The results show that based on the acceleration features, the classification accuracy of lane keeping (LK), lane changing to the left (LCL) and lane changing to the right (LCR) is 100%, 97.89% and 96.19%.