Vehicular Path Prediction for Cooperative Driving Applications through Digital Map and Dynamic Vehicle Model Fusion

This paper investigates the fusion of digital maps and dynamical models to accurately predict the future path of a vehicle. This path prediction is generated by a vehicle for sharing with other vehicles through wireless communication channels. This sharing is an enabler of Vehicle-to-Vehicle (V2V) cooperative systems. In particular, this work looks at cooperative safety and comfort systems, which benefit from accurate path predictions for collision avoidance and coordination with other vehicles. This work proposes that digital map information is valuable in giving a nominal estimate of the future path of the vehicle, and that this estimate can be augmented with realtime vehicle information, such as wheel speeds, yaw rates, and accelerations. Furthermore, dynamic short-term situations such as lane changes can be cleanly incorporated into the vehicular path prediction. Depending on the driving environment, the sensor quality, the map accuracy, and the map matching precision, this paper shows that this fusion has the potential to provide where-in-lane path predictions.