Applying Bayesian nonparametrics to non-homogeneous driving operation data towards prediction

Prediction of driving behaviors is important problem in developing the next-generation driving support system. In order to take account of diverse driving situations, it is necessary to deal with multiple time series data considering commonalities and differences among them. In this study we utilize the beta process autoregressive hidden Markov model (BP-AR-HMM) that can model multiple time series considering common and different features among them using the beta process as a prior distribution. We apply BP-AR-HMM to actual driving operation data to estimate vector-autoregressive process parameters that represent the segmental driving behaviors, and with the estimated parameters we predict the driving behaviors of unknown test data. Prediction accuracy of test data using BP-AR-HMM is compared with that of using classical HMM. The results suggest that it is possible to identify the dynamical behaviors of driving operations using BP-AR-HMM, and with BP-AR-HMM we can predict driving behaviors better in actual environment than with HMM.