Abstract
Human drivers seem to have different characteristics, so different drivers often yield different results from the same driving mode tests with identical vehicles and same chassis dynamometer. However, drivers with different experiences often yield similar results under the same driving conditions. If the features of human drivers are known, the control inputs to each driver, including warnings, will be customized to optimize each man–machine vehicle system. Therefore, it is crucial to determine how to characterize human drivers quantitatively. This study proposes a method to estimate the parameters of a theoretical model of human drivers. The method uses an artificial neural network (ANN) model and a numerical procedure to interpret the identified ANN models theoretically. Our approach involves the following process. First, we specify each ANN driver model through chassis dynamometer tests performed by each human driver and vehicle. Subsequently, we obtain the parameters of a theoretical driver model using the ANN model for the corresponding driver. Specifically, we simulate the driver’s behaviors using the identified ANN models with controlled inputs. Finally, we estimate the theoretical driver model parameters using the numerical simulation results. A proportional-integral-differential (PID) control model is used as the theoretical model. The results of the parameter estimation indicate that the PID driver model parameter combination can characterize human drivers. Moreover, the results suggest that vehicular factors influence the parameter combinations of human drivers.
Similar content being viewed by others
References
Sailer, S., Buchholz, M., & Dietmayer, K. (2011). Flatness based velocity tracking control of a vehicle on a roller dynamometer using a robotic driver. In: The 50th IEEE Conference on Decision and Control and European Control Conference, Orlando, FL, USA (pp. 7962–7967). https://doi.org/10.1109/CDC.2011.6160896.
Sailer, S., Buchholz, M., & Dietmayer, K. (2013). Adaptive model-based velocity control by a robotic driver for vehicles on roller dynamometers. In: American Control Conference, Washington, DC (pp. 1356–1361). https://doi.org/10.1109/ACC.2013.6580025.
Sugihara, Y., Hirose, Y., Furukawa, K., & Ogawa, Y. (2016). Improved method to realize road load simulation for engine test. In: JSAE Autumn Congress. (Autumn), (pp. 2083–2087)
Namik, H., Inamura, T., & Stol, K. (2006). Development of a robotic driver for vehicle dynamometer testing. In: Proceedings of the Australasian Conference on Robotics and Automation. https://www.researchgate.net/publication/237624415.
Mizutani, N., Matsui, H., Yano, K., & Takahashi, T. (2015). Vehicle speed control by a robotic driver using an internal model control considering parametric variations of a vehicle. Journal of the Robotics Society of Japan, 33(10), 818–825. https://doi.org/10.7210/jrsj.33.818
Chen, G., Zhang, W., Li, X., & Yu, B. (2019). Adaptive speed control method for electromagnetic direct drive vehicle robot driver based on fuzzy logic. Measurement and Control, 52(9–10), 1344–1353. https://doi.org/10.1177/0020294019866841
Chen, G., & Zhang, W. (2017). Neural network-based speed control method and experimental verification for electromagnetic direct drive vehicle robot driver. Advances in Mechanical Engineering, 9(12), 1–9. https://doi.org/10.1177/1687814017748237
Zhu, M., Wang, X., & Wang, Y. (2018). Human-like autonomous car-following model with deep reinforcement learning. Transportation Research Part C, 97, 348–368. https://doi.org/10.1016/j.trc.2018.10.024
Ding, C., Wang, W., Wang, X., Rudolf, M., & Baumann, K. (2013). A neural network model for Driver’s lane-changing trajectory prediction in urban traffic flow. Mathematical Problems in Engineering, 2013, 1–14. https://doi.org/10.1155/2013/967358 (Article ID 967358)
Olabiyi, O., Martinson, E., Chintalapudi, V., & Guo, R. (2017). Driver action prediction using deep (bidirectional) recurrent neural network. 1–7. https://doi.org/10.48550/arXiv.1706.02257
Zhang, Y., Chen, Z., & Yuan, Z. (2004). Nonlinear system PID-type multi-step predictive control. Journal of Control Theory and Applications, 2(2), 201–204. https://doi.org/10.1007/s11768-004-0070-2
Sun, J., Liu, F., Si, J., & MEI, S. (2012). Direct heuristic dynamic programming based on an improved PID neural network. Journal of Control Theory and Applications, 10(4), 497–503. https://doi.org/10.1007/s11768-012-0112-0
Zribi, A., Mohamed, C., & Mohamed, D. (2015). A new PID neural network controller design for nonlinear processes. Journal of Circuits, Systems and Computers. https://doi.org/10.1142/S0218126618500652
Marino A., & Neri, F. (2019). PID tuning with neural networks. In: N. Nguyen, F. Gaol, T.P. Hong, B. Trawiński (Eds.), Intelligent Information and Database Systems, ACIIDS 2019. Lecture Notes in Computer Science. Springer. https://doi.org/10.1007/978-3-030-14799-0_41
Zhang, J., Wu, Z., Li, F., Luo, J., Ren, T., Hu, S., Li, W., & Li, W. (2019). Attention-based convolutional and recurrent neural networks for driving behavior recognition using smartphone sensor data. IEEE Access, 7, 148031–148046. https://doi.org/10.1109/ACCESS.2019.2932434
Carvalho, E., Ferreira, B., Ferreira, J., Souza, C., Carvalho, H., Suhara, Y., Pentland, A., & Pessin, G. (2017). Exploiting the use of recurrent neural networks for driver behavior profiling. International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA (pp. 3016–3021). https://doi.org/10.1109/IJCNN.2017.7966230
Cheng, Z., Jeng, L., & Li, K. (2018). Behavioral classification of drivers for driving efficiency related ADAS using artificial neural network. IEEE International Conference on Advanced Manufacturing (ICAM), Yunlin, Taiwan, China (pp. 173–176). https://doi.org/10.1109/AMCON.2018.8614836
Girma, A., Yan, X., & Homaifa, A. (2019). Driver identification based on vehicle telematics data using LSTM-recurrent neural network. In: IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), Portland, OR, USA (pp. 894–902). https://doi.org/10.1109/ICTAI.2019.00127
Cura, A., Kucuk, H., Erge, E., & Oksuzoglu, I. (2021). Driver profiling using long short term memory (LSTM) and convolutional neural network (CNN) methods. IEEE Transactions on Intelligent Transportation Systems, 22(10), 6572–6582. https://doi.org/10.1109/TITS.2020.2995722
Xu, L., Hu, J., Jiang, H., & Meng, W. (2015). Establishing style-oriented driver models by imitating human driving behaviors. IEEE Transactions on Intelligent Transportation Systems, 16(5), 2522–2530. https://doi.org/10.1109/TITS.2015.2409870
Xie, Y., Murphey, Y., & Kochhar, D. (2020). Personalized driver workload estimation using deep neural network learning from physiological and vehicle signals. IEEE Transactions on Intelligent Vehicles, 5(3), 439–448. https://doi.org/10.1109/TIV.2019.2960946
Manawadu, U., Kawano, T., Murata, S., Kamezaki, M., Muramatsu, J., & Sugano, S. (2018). Multiclass classification of driver perceived workload using long short-term memory based recurrent neural network. In: IEEE Intelligent Vehicles Symposium (IV), Changshu, China (pp. 2009–2014). https://doi.org/10.1109/IVS.2018.8500410
Ministry of Land, Infrastructure, Transport and Tourism, Attachment 42 Measuring Method of Exhaust Gas Under Heavy Duty Vehicle. Retrieved 15 Aug 2021. https://www.mlit.go.jp/common/001184850.pdf (in Japanese).
Ruder, S. (2016). An overview of gradient descent optimization algorithms , 1–14. https://doi.org/10.48550/arXiv.1609.04747
Mathew, T. V., & Ravishankar, K. V. R. (2012). Neural network based vehicle-following model for mixed traffic conditions. European Transport, (52), 1–15. http://hdl.handle.net/10077/6094
Levermore, T., Ordys, A., & Deng, J. (2014). A review of driver modelling. In: UKACC International Conference on Control (CONTROL), Loughborough, UK (pp. 296–300). https://doi.org/10.1109/CONTROL.2014.6915156
Summala, H. (2000). Brake reaction times and driver behavior analysis. Transportation Human Factors, 2(3), 217–226.
Droździel, P., Tarkowski, S., Rybicka, I., & Wrona, R. (2020). Drivers’ reaction time research in the conditions in the real traffic. Open Engineering, 10(1), 35–47. https://doi.org/10.1515/eng-2020-0004
Acknowledgements
This work was the result of a collaborative research program with the Research Association of Automotive Internal Combustion Engines (AICE) for the fiscal year 2020. The authors gratefully acknowledge the concerned personnel.
Author information
Authors and Affiliations
Corresponding author
Appendices
Appendix A: Experimental history information
where \(v_{\mathrm{target}}\) is the target speed of the driving modes, \(v_{\mathrm{experiment}}\) is the experimental vehicle speed, and mode distance (km) is the total distance of each driving mode (Table 6).
Appendix B: Additional simulation results
We have performed additional \(K_{P}\) and \(\tau _{D}\) estimations under the \(v_{P}\) and \(a_{D}\) conditions different from those presented in Tables 7 and 8. The results are illustrated in Figs. 11, 12, 13 and 14. A similar trend was observed in the results, as illustrated in Figs. 9 and 10. Differences in K and \(\tau \) were observed depending on the vehicle speed conditions, whereas the trends of \(K_{P}\) and \(\tau _{D}\) depended on the drivers.
All the \(K_{P}\) and \(\tau _{D}\) estimation results in this paper indicate that the tested drivers have different \(K_{P}\)–\(\tau _{D}\) combinations for the three vehicles. In particular, the results for HEV and EV show that the drivers’ \(K_{P}\) and \(\tau _{D}\) data are plotted in different regions in the \(K_{P}\)–\(\tau _{D}\) planes for each driver under all the driving conditions, i.e., all the combinations of the values of v, a, \(v_{P}\), and \(a_{D}\). In addition to that, the \(V_1\) drivers’ plotted data regions in the \(K_{P}\)–\(\tau _{D}\) plane show a similar tendency except for the conditions including the smallest \(v_{P}\), and \(a_{D}\) values. In the case of the smallest \(v_{P}\) and \(a_{D}\) combination, since the influence of the difference between the current and target values is small, the difference in the drivers’ parameters may not be so significant. On the other hand, the results in terms of \(V_2\) show that the tested drivers have almost the same plotted data regions. The vehicle characteristics may cause this.
Rights and permissions
About this article
Cite this article
Kim, S., Miyamoto, T., Kuboyama, T. et al. Characterizing human driver characteristics using an artificial neural network and a theoretical model. Control Theory Technol. 20, 263–278 (2022). https://doi.org/10.1007/s11768-022-00099-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11768-022-00099-7