Clustering of Driving Encounter Scenarios Using Connected Vehicle Trajectories

Abstract

Classification and analysis of driving behaviors offer in-depth knowledge to make an efficient decision for autonomous vehicles. This paper aims to cluster a wide range of driving encounter scenarios based only on multi-vehicle GPS trajectories. Towards this end, we propose a generic unsupervised learning framework comprising of two layers: feature representation layer and clustering layer. In the feature representation layer, we combine the deep autoencoders with a distance-based measure to map the sequential observations of driving encounters into a computationally tractable space, which quantifies the spatiotemporal interaction characteristics of two vehicles. The clustering algorithm is then applied to the extracted representations to cluster homogeneous driving encounters into groups. Our proposed generic framework is then evaluated using 2,568 naturalistic driving encounters. Experimental results show that our proposed generic framework incorporated with unsupervised learning can cluster multi-trajectory data into distinct groups. These clustering results could benefit the decision-making and design of autonomous vehicles.