Inferring the driver´s lane change intention using context-based dynamic Bayesian networks

This paper presents the results of the design and evaluation of a context based intent inference system for highway lane changes. Traditionally, intent inference for this task is based on information from the subject vehicle only. Because the context, e.g. traffic situation, plays an important role in the driver´s situational awareness, a study was performed to investigate what results can be achieved by including this context information in the intent inference system. It was observed that traditional state based systems have a 90% accuracy and reach their maximum performance much earlier than a simple lateral threshold. The addition of various context information variables to the state based system decreased performance, caused by the models having problems capturing the complexity of the context data.