top of page


Mr. John Smith

Job title



An autonomous vehicle control technology can be divided into longitudinal and lateral control. The control algorithm of an autonomous vehicle is used to track the target physical quantity using the accel pedal, brake pedal, steering wheel, and various actuators. To compensate for the disturbance and uncertainty of vehicles with high nonlinearity, it is essential to secure the performance of tracking the target physical quantity using an appropriate control technology. To compensate for this problem, various studies are being conducted in universities and industries on learning-based estimation techniques and various control algorithms for estimating parameters included uncertainty and disturbance of autonomous vehicles. Khan et al. [1] studied a barrier Lyapunov-based SMC to compensate of autonomous vehicles in unstable situations such as road conditions and road curvature. Chen et al. [2] presented High Order Sliding Mode Control (HOSMC) to minimize the chattering phenomenon and proposed a Nonlinear Disturbance Observer (NDOB) to estimate the disturbance of the vehicle dynamics model. Wang et al. [3] presented Back-Stepping Sliding Mode Control (BSSMC) for autonomous lateral control. Norouzi et al. [4] proposed BSSMC using a meta-heuristic optimization algorithm for lateral control of autonomous vehicles. In [1], [2], [3], and [4], SMC, HOSMC, and Back-Stepping techniques were studied for lateral control of autonomous driving. A Sliding Mode Control (SMC) algorithm is robust to disturbance and model uncertainty and is used in autonomous driving and various fields. It has a limitation when excessive disturbance is applied in the model, the control stability is lost. To secure reasonable control performance, adaptive rule and learning-based estimation strategies have been proposed. This paper proposes a Radial Basis Function Neural Network (RBFNN) based on Super-Twisting Sliding Mode Control (STSMC) lateral algorithm to minimize lateral error with yaw rate error for autonomous driving. To design the proposed control algorithm a sliding surface is defined using vehicle lateral error dynamics. The included uncertainty and disturbance in a defined sliding surface estimated using RBFNN. The estimated sliding surface is reflected in the Lyapunov method-based cost function to derive a parameters control input that satisfies the Lyapunov stability conditions. The proposed control algorithm was constructed in Matlab/Simulink environments and CarMaker simulation environments. To evaluate the performance of the proposed controller, SMC, STSMC were compared and evaluated in double lane change scenarios. As a result of the evaluation, when the proposed control algorithm was applied, it was confirmed that the RMS, STD values of the error and chattering phenomenon were minimized than compared control algorithm. However, it was possible to confirm the limit that needs adjustment of control gain values before performance evaluation. Therefore, advanced adaptation and learning-based methodologies for automatic adjustment of control gain will be studied in the future. The control algorithm proposed in this study is expected to be used in various fields, including autonomous vehicles. [1] R. Khan, F. M. Malik, N. Mazhar, A. Raza, R. A. Azim, and H. Ullah, “Robust control framework for lateral dynamics of autonomous vehicle using barrier Lyapunov function,” IEEE Access, vol. 9, pp. 50513-50522, 2021. [2] J. Chen, Z. Shuai, H. Zhang, and W. Zhao, “Path following control of autonomous four-wheel-independent-drive electric vehicles via second-order sliding mode and nonlinear disturbance observer techniques,” IEEE Transactions on Industrial Electronics, vol. 68, no. 3, pp. 2460-2469, 2020. [3] P. Wang, S. Gao, L. Li, S. Cheng, and L. Zhao, “Automatic steering control strategy for unmanned vehicles based on robust backstepping sliding mode control theory,” IEEE Access, vol. 7, pp.64984-64992,2016. [4] A. Norouzi, M. Masoumi, A. Barari, and S. Farrokhpour Sani, “Lateral control of an autonomous vehicle using integrated backstepping and sliding mode controller,” Proceedings of the Institution of Mechanical Engineers, Part K: Journal of Multi-body Dynamics, vol. 233, no. 1, pp. 141-151, 2019.

Prof. Dr. Seok-Cheol Kee, Professor, Chungbuk National University

Super-Twisting Sliding Mode Control with Neural Network for Autonomous Driving

FWC2023-SCA-005 • Integrated safety, connected & automated driving


Sign up or login to the ICC to download this item and access the entire FISITA library.

Upgrade your ICC subscription to access all Library items.

Congratulations! Your ICC subscription gives you complete access to the FISITA Library.


Retrieving info...

Available for purchase on the FISITA Store


bottom of page