Identification of driver operations with extraction of driving primitives

Masayuki Okamoto, Shunsuke Otani, Yasumasa Kaitani, Kenko Uchida

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    11 Citations (Scopus)

    Abstract

    Modeling the driver behavior is expected to play a fundamental role in designing systems of driver monitoring, warning, assist control and training. In this paper, we present an identification method of automobile driver operations based on a hierarchical clustering approach, which leads to a stochastic piecewise affine (PWA) model. The driver behavior can be viewed as an outcome of the hybrid system that consists of (continuous) primitive driving operations and their (discrete) switchings. We describe the driving primitives by PWA models and the switchings by hidden Markov models (HMMs). One significant issue of this hybrid modeling is to extract the distinct states of driving operation from the driver behavior and determine the number of the states. To this problem, we propose a method to estimate the number of states using an idea of hierarchical clustering. We apply our identification method to the accelerator operations of driver, and demonstrate its efficacy through numerical experiments using the real data of four drivers.

    Original languageEnglish
    Title of host publicationProceedings of the IEEE International Conference on Control Applications
    Pages338-344
    Number of pages7
    DOIs
    Publication statusPublished - 2011
    Event2011 20th IEEE International Conference on Control Applications, CCA 2011 - Denver, CO
    Duration: 2011 Sep 282011 Sep 30

    Other

    Other2011 20th IEEE International Conference on Control Applications, CCA 2011
    CityDenver, CO
    Period11/9/2811/9/30

    Fingerprint

    Driver
    Automobile drivers
    Hidden Markov models
    Hybrid systems
    Particle accelerators
    Hierarchical Clustering
    Monitoring
    Hybrid Modeling
    Experiments
    Automobile
    Accelerator
    Hybrid Systems
    Markov Model
    Efficacy
    Numerical Experiment
    Distinct
    Modeling
    Model
    Estimate
    Demonstrate

    ASJC Scopus subject areas

    • Control and Systems Engineering
    • Computer Science Applications
    • Mathematics(all)

    Cite this

    Okamoto, M., Otani, S., Kaitani, Y., & Uchida, K. (2011). Identification of driver operations with extraction of driving primitives. In Proceedings of the IEEE International Conference on Control Applications (pp. 338-344). [6044425] https://doi.org/10.1109/CCA.2011.6044425

    Identification of driver operations with extraction of driving primitives. / Okamoto, Masayuki; Otani, Shunsuke; Kaitani, Yasumasa; Uchida, Kenko.

    Proceedings of the IEEE International Conference on Control Applications. 2011. p. 338-344 6044425.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Okamoto, M, Otani, S, Kaitani, Y & Uchida, K 2011, Identification of driver operations with extraction of driving primitives. in Proceedings of the IEEE International Conference on Control Applications., 6044425, pp. 338-344, 2011 20th IEEE International Conference on Control Applications, CCA 2011, Denver, CO, 11/9/28. https://doi.org/10.1109/CCA.2011.6044425
    Okamoto M, Otani S, Kaitani Y, Uchida K. Identification of driver operations with extraction of driving primitives. In Proceedings of the IEEE International Conference on Control Applications. 2011. p. 338-344. 6044425 https://doi.org/10.1109/CCA.2011.6044425
    Okamoto, Masayuki ; Otani, Shunsuke ; Kaitani, Yasumasa ; Uchida, Kenko. / Identification of driver operations with extraction of driving primitives. Proceedings of the IEEE International Conference on Control Applications. 2011. pp. 338-344
    @inproceedings{fd85062ae4d84063a1a6318dd8b4066a,
    title = "Identification of driver operations with extraction of driving primitives",
    abstract = "Modeling the driver behavior is expected to play a fundamental role in designing systems of driver monitoring, warning, assist control and training. In this paper, we present an identification method of automobile driver operations based on a hierarchical clustering approach, which leads to a stochastic piecewise affine (PWA) model. The driver behavior can be viewed as an outcome of the hybrid system that consists of (continuous) primitive driving operations and their (discrete) switchings. We describe the driving primitives by PWA models and the switchings by hidden Markov models (HMMs). One significant issue of this hybrid modeling is to extract the distinct states of driving operation from the driver behavior and determine the number of the states. To this problem, we propose a method to estimate the number of states using an idea of hierarchical clustering. We apply our identification method to the accelerator operations of driver, and demonstrate its efficacy through numerical experiments using the real data of four drivers.",
    author = "Masayuki Okamoto and Shunsuke Otani and Yasumasa Kaitani and Kenko Uchida",
    year = "2011",
    doi = "10.1109/CCA.2011.6044425",
    language = "English",
    isbn = "9781457710629",
    pages = "338--344",
    booktitle = "Proceedings of the IEEE International Conference on Control Applications",

    }

    TY - GEN

    T1 - Identification of driver operations with extraction of driving primitives

    AU - Okamoto, Masayuki

    AU - Otani, Shunsuke

    AU - Kaitani, Yasumasa

    AU - Uchida, Kenko

    PY - 2011

    Y1 - 2011

    N2 - Modeling the driver behavior is expected to play a fundamental role in designing systems of driver monitoring, warning, assist control and training. In this paper, we present an identification method of automobile driver operations based on a hierarchical clustering approach, which leads to a stochastic piecewise affine (PWA) model. The driver behavior can be viewed as an outcome of the hybrid system that consists of (continuous) primitive driving operations and their (discrete) switchings. We describe the driving primitives by PWA models and the switchings by hidden Markov models (HMMs). One significant issue of this hybrid modeling is to extract the distinct states of driving operation from the driver behavior and determine the number of the states. To this problem, we propose a method to estimate the number of states using an idea of hierarchical clustering. We apply our identification method to the accelerator operations of driver, and demonstrate its efficacy through numerical experiments using the real data of four drivers.

    AB - Modeling the driver behavior is expected to play a fundamental role in designing systems of driver monitoring, warning, assist control and training. In this paper, we present an identification method of automobile driver operations based on a hierarchical clustering approach, which leads to a stochastic piecewise affine (PWA) model. The driver behavior can be viewed as an outcome of the hybrid system that consists of (continuous) primitive driving operations and their (discrete) switchings. We describe the driving primitives by PWA models and the switchings by hidden Markov models (HMMs). One significant issue of this hybrid modeling is to extract the distinct states of driving operation from the driver behavior and determine the number of the states. To this problem, we propose a method to estimate the number of states using an idea of hierarchical clustering. We apply our identification method to the accelerator operations of driver, and demonstrate its efficacy through numerical experiments using the real data of four drivers.

    UR - http://www.scopus.com/inward/record.url?scp=80155192491&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=80155192491&partnerID=8YFLogxK

    U2 - 10.1109/CCA.2011.6044425

    DO - 10.1109/CCA.2011.6044425

    M3 - Conference contribution

    AN - SCOPUS:80155192491

    SN - 9781457710629

    SP - 338

    EP - 344

    BT - Proceedings of the IEEE International Conference on Control Applications

    ER -