Development of driving intention prediction system based on human cognitive mechanism

Tsuyoshi Sakuma, Satoshi Miura, Tomoyuki Miyashita, Masakatsu G. Fujie, Shigeki Sugano

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

    1 Citation (Scopus)

    Abstract

    The advance of driving assistance technologies such as Electronic Stability Control (ESC) or auto break system, drivers are released from complicated driving tasks. On the other hand, there is concern that it reduces pleasure feelings of a driver if these system's behaviors are different from the driver's intention. To avoid such problem, it is important to evaluate the driver's intention and decision-making process, and design the assistance system to fit it. Although methods such as sensory subjective evaluation are commonly used, the human cognitive mechanism design behind them is not yet fully understood. In this paper, we introduce a novel method for evaluating driver's decision-making process based on the numerical simulation of the driver's behavior. By using this method, the assistance system can substitute the driver appropriately and driver can accept the system's maneuver because which is same as the driver's intention. As an example of this method we evaluate the relationship between decision-making timing and estimation time length of the driver's model. One possible method to simulate the driver's decision-making is machine learning. Reinforcement learning has been studied for simulating the human's brain function to learn and decide as action and state model. We used machine learning to create the reinforcement learning driver model, and a simple vehicle simulation model which are combined as a human-vehicle model. We used the simple vehicle and driver model because the aim of this research is to investigate whether the driver's decision-making process can be simulated or not. Then the model is simulated to learn to drive on a highway with 3 lanes and other vehicles. The simulated driver made some single lane change to pass a slower vehicle in front or to go out from highway at an interchange. Results showed that the decision-making timing depend on the estimation time of the reinforcement learning model. We exposed that the model behaves similar to general driver's behavior when the estimation time was settled as 7sec which is derived from human brain's cognitive mechanism. In conclusion, our simulation model based on human cognitive mechanism can simulate the driver's lane change decision-making behavior adequately.

    Original languageEnglish
    Title of host publication2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages573-578
    Number of pages6
    ISBN (Electronic)9781538668689
    DOIs
    Publication statusPublished - 2019 Jan 22
    Event2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018 - Kandima, Maldives
    Duration: 2018 Aug 12018 Aug 5

    Publication series

    Name2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018

    Conference

    Conference2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018
    CountryMaldives
    CityKandima
    Period18/8/118/8/5

    Fingerprint

    Driver
    Prediction
    Decision making
    Reinforcement learning
    Decision Making
    Reinforcement Learning
    Learning systems
    Brain
    Human
    Model
    Interchanges
    Timing
    Machine Learning
    Simulation Model
    Sensory Evaluation
    Subjective Evaluation
    Mechanism Design
    Evaluate
    Substitute
    Computer simulation

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Control and Optimization

    Cite this

    Sakuma, T., Miura, S., Miyashita, T., Fujie, M. G., & Sugano, S. (2019). Development of driving intention prediction system based on human cognitive mechanism. In 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018 (pp. 573-578). [8621765] (2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/RCAR.2018.8621765

    Development of driving intention prediction system based on human cognitive mechanism. / Sakuma, Tsuyoshi; Miura, Satoshi; Miyashita, Tomoyuki; Fujie, Masakatsu G.; Sugano, Shigeki.

    2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018. Institute of Electrical and Electronics Engineers Inc., 2019. p. 573-578 8621765 (2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018).

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

    Sakuma, T, Miura, S, Miyashita, T, Fujie, MG & Sugano, S 2019, Development of driving intention prediction system based on human cognitive mechanism. in 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018., 8621765, 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018, Institute of Electrical and Electronics Engineers Inc., pp. 573-578, 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018, Kandima, Maldives, 18/8/1. https://doi.org/10.1109/RCAR.2018.8621765
    Sakuma T, Miura S, Miyashita T, Fujie MG, Sugano S. Development of driving intention prediction system based on human cognitive mechanism. In 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 573-578. 8621765. (2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018). https://doi.org/10.1109/RCAR.2018.8621765
    Sakuma, Tsuyoshi ; Miura, Satoshi ; Miyashita, Tomoyuki ; Fujie, Masakatsu G. ; Sugano, Shigeki. / Development of driving intention prediction system based on human cognitive mechanism. 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 573-578 (2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018).
    @inproceedings{488387942b554f749b231e17bd94dc9b,
    title = "Development of driving intention prediction system based on human cognitive mechanism",
    abstract = "The advance of driving assistance technologies such as Electronic Stability Control (ESC) or auto break system, drivers are released from complicated driving tasks. On the other hand, there is concern that it reduces pleasure feelings of a driver if these system's behaviors are different from the driver's intention. To avoid such problem, it is important to evaluate the driver's intention and decision-making process, and design the assistance system to fit it. Although methods such as sensory subjective evaluation are commonly used, the human cognitive mechanism design behind them is not yet fully understood. In this paper, we introduce a novel method for evaluating driver's decision-making process based on the numerical simulation of the driver's behavior. By using this method, the assistance system can substitute the driver appropriately and driver can accept the system's maneuver because which is same as the driver's intention. As an example of this method we evaluate the relationship between decision-making timing and estimation time length of the driver's model. One possible method to simulate the driver's decision-making is machine learning. Reinforcement learning has been studied for simulating the human's brain function to learn and decide as action and state model. We used machine learning to create the reinforcement learning driver model, and a simple vehicle simulation model which are combined as a human-vehicle model. We used the simple vehicle and driver model because the aim of this research is to investigate whether the driver's decision-making process can be simulated or not. Then the model is simulated to learn to drive on a highway with 3 lanes and other vehicles. The simulated driver made some single lane change to pass a slower vehicle in front or to go out from highway at an interchange. Results showed that the decision-making timing depend on the estimation time of the reinforcement learning model. We exposed that the model behaves similar to general driver's behavior when the estimation time was settled as 7sec which is derived from human brain's cognitive mechanism. In conclusion, our simulation model based on human cognitive mechanism can simulate the driver's lane change decision-making behavior adequately.",
    author = "Tsuyoshi Sakuma and Satoshi Miura and Tomoyuki Miyashita and Fujie, {Masakatsu G.} and Shigeki Sugano",
    year = "2019",
    month = "1",
    day = "22",
    doi = "10.1109/RCAR.2018.8621765",
    language = "English",
    series = "2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    pages = "573--578",
    booktitle = "2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018",

    }

    TY - GEN

    T1 - Development of driving intention prediction system based on human cognitive mechanism

    AU - Sakuma, Tsuyoshi

    AU - Miura, Satoshi

    AU - Miyashita, Tomoyuki

    AU - Fujie, Masakatsu G.

    AU - Sugano, Shigeki

    PY - 2019/1/22

    Y1 - 2019/1/22

    N2 - The advance of driving assistance technologies such as Electronic Stability Control (ESC) or auto break system, drivers are released from complicated driving tasks. On the other hand, there is concern that it reduces pleasure feelings of a driver if these system's behaviors are different from the driver's intention. To avoid such problem, it is important to evaluate the driver's intention and decision-making process, and design the assistance system to fit it. Although methods such as sensory subjective evaluation are commonly used, the human cognitive mechanism design behind them is not yet fully understood. In this paper, we introduce a novel method for evaluating driver's decision-making process based on the numerical simulation of the driver's behavior. By using this method, the assistance system can substitute the driver appropriately and driver can accept the system's maneuver because which is same as the driver's intention. As an example of this method we evaluate the relationship between decision-making timing and estimation time length of the driver's model. One possible method to simulate the driver's decision-making is machine learning. Reinforcement learning has been studied for simulating the human's brain function to learn and decide as action and state model. We used machine learning to create the reinforcement learning driver model, and a simple vehicle simulation model which are combined as a human-vehicle model. We used the simple vehicle and driver model because the aim of this research is to investigate whether the driver's decision-making process can be simulated or not. Then the model is simulated to learn to drive on a highway with 3 lanes and other vehicles. The simulated driver made some single lane change to pass a slower vehicle in front or to go out from highway at an interchange. Results showed that the decision-making timing depend on the estimation time of the reinforcement learning model. We exposed that the model behaves similar to general driver's behavior when the estimation time was settled as 7sec which is derived from human brain's cognitive mechanism. In conclusion, our simulation model based on human cognitive mechanism can simulate the driver's lane change decision-making behavior adequately.

    AB - The advance of driving assistance technologies such as Electronic Stability Control (ESC) or auto break system, drivers are released from complicated driving tasks. On the other hand, there is concern that it reduces pleasure feelings of a driver if these system's behaviors are different from the driver's intention. To avoid such problem, it is important to evaluate the driver's intention and decision-making process, and design the assistance system to fit it. Although methods such as sensory subjective evaluation are commonly used, the human cognitive mechanism design behind them is not yet fully understood. In this paper, we introduce a novel method for evaluating driver's decision-making process based on the numerical simulation of the driver's behavior. By using this method, the assistance system can substitute the driver appropriately and driver can accept the system's maneuver because which is same as the driver's intention. As an example of this method we evaluate the relationship between decision-making timing and estimation time length of the driver's model. One possible method to simulate the driver's decision-making is machine learning. Reinforcement learning has been studied for simulating the human's brain function to learn and decide as action and state model. We used machine learning to create the reinforcement learning driver model, and a simple vehicle simulation model which are combined as a human-vehicle model. We used the simple vehicle and driver model because the aim of this research is to investigate whether the driver's decision-making process can be simulated or not. Then the model is simulated to learn to drive on a highway with 3 lanes and other vehicles. The simulated driver made some single lane change to pass a slower vehicle in front or to go out from highway at an interchange. Results showed that the decision-making timing depend on the estimation time of the reinforcement learning model. We exposed that the model behaves similar to general driver's behavior when the estimation time was settled as 7sec which is derived from human brain's cognitive mechanism. In conclusion, our simulation model based on human cognitive mechanism can simulate the driver's lane change decision-making behavior adequately.

    UR - http://www.scopus.com/inward/record.url?scp=85062487025&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85062487025&partnerID=8YFLogxK

    U2 - 10.1109/RCAR.2018.8621765

    DO - 10.1109/RCAR.2018.8621765

    M3 - Conference contribution

    T3 - 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018

    SP - 573

    EP - 578

    BT - 2018 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2018

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -