Car-following systems using a multilayer type-2 fuzzy neural network integrated with recurrent neural networks

Ngo, Van Binh; Le, Loc Tien

doi:10.22111/ijfs.2026.55222.9795

Articles in Press

Document Type : Original Manuscript

Authors

Faculty of Mechatronics Engineering, Lac Hong University, Dong Nai, Vietnam

https://doi.org/10.22111/ijfs.2026.55222.9795

Abstract

Car-following systems play a critical role in advanced driver assistance systems and autonomous driving applications, where accurate detection and stable tracking of the preceding vehicle are essential for ensuring safety and smooth motion. This paper presents a low-cost vision-based car-following control system that combines monocular vision sensing with an intelligent speed controller. A convolutional neural network is employed to detect the target vehicle and extract spatial information from input images, while the measured distance is refined using a Kalman filter to suppress noise and improve estimation stability. Based on the visual feedback, the vehicle speed is regulated by a Recurrent Multilayer Interval Type-2 Fuzzy Neural Network (RMIT2FNN), enabling adaptive responses to the motion of the leading vehicle and maintenance of a safe following distance. The proposed approach is first validated through simulations, in which its tracking performance is compared with conventional FNN and IT2FNN controllers under the same operating conditions. The simulation results demonstrate improved tracking accuracy and rapid responses to velocity variations. Subsequently, real-time experimental validation is conducted on a 1/10-scale vehicle platform, confirming that the system can detect and track the preceding vehicle stably while maintaining the desired following distance under indoor operating conditions. These findings provide preliminary evidence of the feasibility of the proposed method as a cost- efficient vision-based car-following solution under controlled experimental conditions.

Keywords

Main Subjects

Engineering

References

[1] H. U. Ahmed, Y. Huang, P. Lu, A review of car-following models and modeling tools for human and autonomous ready driving behaviors in micro-simulation, Smart Cities, 4(1) (2021), 314-335. https://doi.org/10.3390/ smartcities4010019

[2] G. Alite, Å. Cuenca, J. Salt, M. Tomizuka, Resource-efficient path-following control for a self-driving car in a networked control system, IEEE Access, 11 (2023), 108011-108023. https://doi.org/10.1109/ACCESS.2023. 3321269

[3] S. Askari, S. Zarei, A fuzzy clustering-based genetic TSK system with fuzzy IF part parameters and nonlinear THEN part, Iranian Journal of Fuzzy Systems, 22(6) (2025), 41-65. https://doi.org/10.22111/ijfs.2025.51929.9165

[4] J. Bai, S. Mao, J. J. Lee, A novel car-following model for adaptive cruise control vehicles using enhanced intelligent driver model, Transportation Letters, 17(4) (2025), 702-718. https://doi.org/10.1080/19427867.2024.2376409

[5] Y. Chen, C. Dong, K. Lyu, et al., A review of car-following and lane-changing models under heterogeneous environments, Physica A: Statistical Mechanics and its Applications, 654 (2024), 130127. https://doi.org/10.1016/j. physa.2024.130127

[6] W. Cheng, F. Gao, Y. Li, et al., A machine vision-based dimension measurement method of shaft parts with sub-pixel edge, Measurement Science and Technology, 36(5) (2025), 055026. https://doi.org/10.1088/1361-6501/adcc47

[7] Y. Fu, W. Hu, J. Shang, et al., A fractional-order car-following model with random delay optimized by an enhanced whale optimization algorithm, Nonlinear Dynamics, 113(16) (2025), 21277-21303. https://doi.org/10.1007/ s11071-025-11271-4

[8] N. M. Hung, H. H. Viet, T. L. Le, A hybrid parallel decomposed interval type-2 fuzzy-Jordan neural network for controlling uncertain ball-and-beam systems, Physica Scripta, 101(7) (2026), 076007. https://doi.org/10.1088/ 1402-4896/ae442b

[9] M. L. Lagunes, O. Castillo, F. Valdez, J. Soria, Comparison of fuzzy controller optimization with dynamic parameter adjustment based on of Type-1 and Type-2 fuzzy logic, Hybrid Intelligent Systems in Control, Pattern Recognition and Medicine, Springer, Cham, (2020), 47-56. https://doi.org/10.1007/978-3-030-34135-0_4

[10] L. T. Le, L. K. Ngo, Application of combining Type 2 fuzzy CMAC network and Jordan neural network in nonlinear system control, Iranian Journal of Fuzzy Systems, 22(2) (2025), 25-39. https://doi.org/10.22111/ijfs.2025. 50552.8930

[11] W. Lu, Z. Yi, B. Liang, et al., Learning car-following behaviors for a connected automated vehicle system: An improved sequence-to-sequence deep learning model, IEEE Access, 11 (2023), 28076-28089. https://doi.org/10. 1109/ACCESS.2023.3243620

[12] H. Ma, J. Qiu, G. Sheng, et al., Deep simple recurrent unit-based transient modeling method for high-speed circuits, IEEE Transactions on Microwave Theory and Techniques, 73(2) (2025), 736-744. https://doi.org/10.1109/ TMTT.2024.3426595

[13] M. Mazandarani, M. Najariyan, Perception-informed neural networks: Beyond physics-informed neural networks, arXiv preprint, (2025). https://doi.org/10.48550/arXiv.2505.03806

[14] M. D. Pop, Selection of defuzzification method for calibrating car-following models using Mamdani FIS, 2025 International Conference on Smart Applications, Communications and Networking (SmartNets), Istanbul, Türkiye, (2025), 1-6. https://doi.org/10.1109/SmartNets65254.2025.11106770

[15] Y. Qin, M. Liu, W. Hao, Energy-optimal car-following model for connected automated vehicles considering traffic flow stability, Energy, 298 (2024), 131333. https://doi.org/10.1016/j.energy.2024.131333

[16] B. Qiu, H. Kuang, A comprehensive review of dynamic modeling methods for extended optimal velocity car following models in traffic flow, Nonlinear Dynamics, 113(10) (2025), 10861-10879. https://doi.org/10.1007/ s11071-024-10660-5

[17] V. Shah, H. Patel, Integrating machine learning and computer vision in advanced driver assistance systems: A com prehensive review, Augmented Human Research, 11(1) (2026). https://doi.org/10.1007/s41133-025-00086-y

[18] C. S. Shih, P. W. Huang, E. T. Yen, P. K. Tsung, Vehicle speed prediction with RNN and attention model under multiple scenarios, 2019 IEEE Intelligent Transportation Systems Conference (ITSC), Auckland, New Zealand, (2019), 369-375. https://doi.org/10.1109/ITSC.2019.8917479

[19] A. Si, S. Das, MFS: Dynamic decision-making approach to select optimal alternative in the presence of uncertainty, Iranian Journal of Fuzzy Systems, 22(2) (2025), 81-95. https://doi.org/10.22111/ijfs.2025.49694.8773

[20] V. Siwach, D. Yadav, P. Redhu, Enhancing driver’s attention and overtaking efficiency in car-following model for Advanced Driver Assistance Systems (ADAS) vehicles, Physica A: Statistical Mechanics and its Applications, 657 (2025), 130207. https://doi.org/10.1016/j.physa.2024.130207

[21] S. Tiwari, A. Gehlot, R. Singh, et al., Design of an iterative method for disease prediction in finger millet leaves using graph networks, dyna networks, autoencoders, and recurrent neural networks, Results in Engineering, 24 (2024), 103301. https://doi.org/10.1016/j.rineng.2024.103301

[22] P. V. Toan, T. L. Le, Parallel hybrid interval type-2 fuzzy NARX network for robust line-following control of autonomous guided vehicles, Measurement Science and Technology, 37(10) (2026), 106201. https://doi.org/10. 1088/1361-6501/ae4bf8

[23] M. Treiber, A. Kesting, Car-following models based on driving strategies, Traffic Flow Dynamics, Springer, Cham, (2025), 239-284. https://doi.org/10.1007/978-3-642-32460-4_11

[24] C. Urrea, C. Domínguez, J. Kern, Modeling, design and control of a 4-arm delta parallel manipulator employing Type-1 and interval Type-2 fuzzy logic-based techniques for precision applications, Robotics and Autonomous Systems, 175 (2024), 104661. https://doi.org/10.1016/j.robot.2024.104661

[25] Z. Wang, Y. Shi, W. Tong, et al., Car-following models for human-driven vehicles and autonomous vehicles: A systematic review, Journal of Transportation Engineering, Part A: Systems, 149(8) (2023), 04023075. https: //doi.org/10.1061/JTEPBS.TEENG-7836

[26] W. Xiao, G. Xie, H. Liu, et al., FDAN: Fuzzy deep attention networks for driver behavior recognition, Journal of Systems Architecture, 147 (2024), 103063. https://doi.org/10.1016/j.sysarc.2023.103063

[27] W. Yang, B. Sun, G. Ma, H. Sun, Car-following modeling with multi-model driving assistance and stability analysis under heterogeneous time delay, Chaos, Solitons and Fractals, 204 (2026), 117679. https://doi.org/10.1016/j. chaos.2025.117679

[28] D. Yang, S. Wang, Y. Liao, R. Pan, An online energy management strategy for fuel cell vehicles based on fuzzy Q-learning and road condition recognition, IEEE Transactions on Intelligent Transportation Systems, 25(9) (2024), 12120-12130. https://doi.org/10.1109/TITS.2024.3368149

[29] L. A. Zadeh, Fuzzy sets, Information and Control, 8(3) (1965), 338-353. https://doi.org/10.1016/ S0019-9958(65)90241-X

[30] Y. Zha, J. Deng, Y. Qiu, et al., A survey of intelligent driving vehicle trajectory tracking based on vehicle dynamics, SAE International Journal of Vehicle Dynamics, Stability, and NVH, 7(2) (2023), 221-248. https://doi.org/10. 4271/10-07-02-0014

[31] T. T. Zhang, P. J. Jin, S. T. McQuade, et al., Car-following models: A multidisciplinary review, IEEE Transactions on Intelligent Vehicles, 10(1) (2025), 92-116. https://doi.org/10.1109/TIV.2024.3409468

[32] Y. Zhou, R. Fu, C. Wang, Learning the car-following behavior of drivers using maximum entropy deep inverse reinforcement learning, Journal of Advanced Transportation, 2020 (2020), 4752651. https://doi.org/10.1155/ 2020/4752651

Car-following systems using a multilayer type-2 fuzzy neural network integrated with recurrent neural networks

References

References

Articles in Press, Accepted Manuscript Available Online from 28 September 2026

Articles in Press, Accepted Manuscript
Available Online from 28 September 2026