Transfer of Personal Driving Styles to Autonomous Vehicles

Abstract

This paper presents a learning model that can be implemented on autonomous vehicles, using a dedicated software platform, based on physics, which can also be used to track the behavior of components and subsystems of the vehicle. In order to prepare the data for entering the software platform, data (position, orientation, acceleration, instantaneous speed) were recorded from a vehicle driven by several drivers on a previously established route. By processing the data, a driving style was established based on the average values recorded, for each subject who participated in the experimental tests. A virtual environment was created to correspond to the real route in which an autonomous vehicle was modeled and the data on the previously established driving style (instantaneous speeds vs. positions) were transferred. Following the running in the virtual environment and the registration of the data about the behavior of the vehicle on the established route, the data obtained by the classical method and the virtual simulation were compared. Thus, corrections can be made on the speed profile implemented for the autonomous vehicle, in order to comply with the limits imposed by the use of this vehicle with passengers: speed limits, longitudinal and lateral acceleration limits, braking limits.

Keywords

• Autonomous vehicle
• Driving style
• Driver behavior
• Simulation.

References

1. Grippenkoven, J. and Dietsch, S. (2016). Gaze direction and driving behavior of drivers at level crossings. Journal of Transportation Safety & Security, 8(1), 4-18. DOI: 10.1080/19439962.2015.1046620.
2. Kaplan, S., Guvensan, M. A., Yavuz, A. G., & Karalurt, Y. (2015). Driver behavior analysis for safe driving: A survey. IEEE Transactions on Intelligent Transportation Systems, 16(6), 3017-3032. DOI: 10.1109/TITS.2015.2462084.
3. Martinez, C. M., Heucke, M., Wang, F. Y., Gao, B., & Cao, D. (2017). Driving style recognition for intelligent vehicle control and advanced driver assistance: A survey. Transactions on Intelligent Transportation Systems, 19(3), 666-676. doi: 10.1109/TITS.2017.2706978.
4. Mathworks (2021, September 28)PreScanSimulation of ADAS and active safety. https://ch.mathworks.com/products/connections/product_detail/prescan.html.
5. McDonald, A. D., Alambeigi, H., Engström, J., Markkula, G., Vogelpohl, T., Dunne, J., & Yuma, N. (2019). Toward computational simulations of behavior during automated driving takeovers: a review of the empirical and modeling literatures. Human Factors, 61(4), 642-688. doi: 10.1177/0018720819829572.
6. Scherer, S., Dettmann, A., Hartwich, F., Pech, T., Bullinger, A. C., & Wanielik, G. (2015, November). How the driver wants to be driven-modelling driving styles in highly automated driving [Conference presentation]. 7. Tagung Fahrerassistenzsysteme. Munich.
7. Shi, B., Xu, L., Hu, J., Tang, Y., Jiang, H., Meng, W., & Liu, H. (2015). Evaluating driving styles by normalizing driving behavior based on personalized driver modeling. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 45(12), 1502-1508. doi: 10.1109/TSMC.2015.2417837.
8. Shinar, D., & Oppenheim, I. (2011). Review of models of driver behaviour and development of a unified driver behaviour model for driving in safety critical situations. In Human Modelling in Assisted Transportation (pp. 215-223). Springer. https://doi.org/10.1007/978-88-470-1821-1_23.

9. Siemens (2021, September 2). Simcenter Prescan - Develop more reliable and safer automated vehicle functionalities.
10. https://www.plm.automation.siemens.com/global/en/products/simcenter/prescan.html, acc sept.2, 2021.
11. Van Ly, M., Martin, S., & Trivedi, M. M. (2013, June). Driver classification and driving style recognition using inertial sensors. In 2013 IEEE Intelligent Vehicles Symposium (IV) (pp. 1040-1045). IEEE. doi: 10.1109/IVS.2013.6629603.
12. Zhu, M., Wang, X., & Wang, Y. (2018). Human-like autonomous car-following model with deep reinforcement learning. Transportation Research Part C: Emerging Technologies, 97, 348-368. https://doi.org/10.1016/j.trc.2018.10.024.