Similar articles

Abstract: We propose a model structure with a double-layer hidden Markov model (HMM) to recognise driving intention and predict driving behaviour. The upper-layer multi-dimensional discrete HMM (MDHMM) in the double-layer HMM represents driving intention in a combined working case, constructed according to the driving behaviours in certain single working cases in the lower-layer multi-dimensional Gaussian HMM (MGHMM). The driving behaviours are recognised by manoeuvring the signals of the driver and vehicle state information, and the recognised results are sent to the upper-layer HMM to recognise driving intentions. Also, driving behaviours in the near future are predicted using the likelihood-maximum method. A real-time driving simulator test on the combined working cases showed that the double-layer HMM can recognise driving intention and predict driving behaviour accurately and efficiently. As a result, the model provides the basis for pre-warning and intervention of danger and improving comfort performance.

[1]Beyon, J.Y., 2000. LabVIEW: Programming, Data Acquisition and Analysis (1st Ed.). Prentice Hall PTR, Upper Saddle River, New Jersey, USA.

[2]Cappé, O., Moulines, E., Rydén, T., 2005. Inference in Hidden Markov Models. Springer, USA.

[3]Chen, S.G., Ji, S.Y., Liu, W.S., Song, Z.Y., Pang, L.J., 2009. Recursive implementation of Gaussian pulse shaping based on wavelet analysis. Acta Phys. Sin., 58(5):3041-3046 (in Chinese).

[4]Ge, M.L., 2006. Study on the Automatic Control of Hill-Start Assist System for AMT System. MS Thesis, Jilin University, Changchun, China (in Chinese).

[5]Guo, K.H., Guan, H., Zong, C.F., 1999. Development and Applications of JUT-ADSL Driving Simulator. Proc. IEEE Int. Vehicle Electronics Conf., p.1-5.

[6]Kishimoto, Y., Oguri, K., 2008. A Modeling Method for Predicting Driving Behavior Concerning with Driver’s Past Movements. Proc. IEEE Int. Conf. on Vehicular Electronics and Safety, p.132-136.

[7]Kuge, N., Yamamura, T., Shimoyama, O., 2000. A Driver Behavior Recognition Method Based on a Driver Model Framework. SAE Paper, Detroit, USA, No. 2000-01-0349.

[8]Meng, X.N., Lee, K.K., Xu, Y.S., 2006. Human Driving Behavior Recognition Based on Hidden Markov Models. Proc. IEEE Int. Conf. on Robotics and Biomimetics, p.274-279.

[9]Oliver, N., Garg, A., Horvitz, E., 2004. Representations for learning and inferring office activity from multiple sensory channels. Comput. Vis. Image Understand., 96(2):163-180.

[10]Pentland, A., Liu, A., 1999. Modeling and prediction of human behavior. Neur. Comput., 11(1):229-242.

[11]Rabiner, L.R., 1989. A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE, 77(2):257-286.

[12]Raksincharoensak, P., Mizushima, T., Nagai, M., 2008. Direct yaw moment control system based on driver behavior recognition. Veh. Syst. Dyn., 46(sup1):911-921.

[13]Takano, W., Matsushita, A., Iwao, K., Nakamura, Y., 2008. Recognition of Human Driving Behaviors Based on Stochastic Symbolization of Time Series Signal. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, p.167-172.

[14]Wang, W.Z., 2000. t test—the superlative test to discard abnormal values with σ unknown. J. Sichuan Univ. Sci. Technol., 19(3):84-86 (in Chinese).

[15]Xi, Z., Levinson, D., 2006. Modeling intersection driving behaviors: a hidden Markov model approach (I). J. Transp. Res. Board, p.16-23.