Neural Network Sliding Mode Control of Intelligent Vehicle Longitudinal Dynamics

Abstract

Longitudinal dynamics control is the basis for autonomous driving of intelligent vehicles, which have great significance to the development of intelligent transportation system (ITS). To solve the problems of traditional sliding mode control method when applied to intelligent vehicle longitudinal dynamics, such as large velocity tracking errors, strong chattering phenomenon and so on, a new sliding mode control strategy based on RBF (Radical Basis Function) neural network is presented in this paper. Firstly, a nonlinear mathematical model of the intelligent vehicle longitudinal motion is established by considering the dynamics of the engine, the torque converter, the automatic transmission and the brake system. On the basis of the system model, a variable structure control system with sliding mode is introduced to design a sliding mode variable controller with RBF neural network. This controller can adaptively adjust the switching gain and its stability is proved based on the Lyapunov theory. Finally, the effectiveness of the designed longitudinal velocity control strategy is verified by simulation under typical driving conditions. The simulation results show that the improved control algorithm can effectively suppress chattering, obtain the higher precision and stronger robustness than the traditional sliding mode control. Thus, the longitudinal motion control performance of intelligent vehicles is improved effectively. INDEX TERMS Intelligent vehicles, intelligent transportation system, longitudinal dynamics control, sliding mode control, RBF neural network.

An extensive critique of sliding mode control and adaptive neuro‐fuzzy inference system for nonlinear system

“…As inked in Wang et al [5], traditional SMC and RBF‐NTSMC (outspread premise work nonsolitary terminal SMC) are applied for longitudinal speed control. The principle point is to give a precise and predictable quickening following control of the vehicle longitudinal speed.…”

“…The movement of the framework as it slides along these limits is known as a sliding mode, and the mathematical locus comprising of the limits is known as the sliding (hyper) surface. According to Wang et al [5], traditional SMC and radial basis function nonsingular terminal SMC (RBF‐NTSMC) are applied for longitudinal speed control, which is to give a precise and predictable quickening following control of the vehicle longitudinal speed. RBF‐NTSMC reduces relative speed errors and throttle's response during longitudinal speed control and also reduces the chattering of the system.…”

Robust EMRAN-aided coupled controller for autonomous vehicles

“…The BVSC steers the vehicle, while the RBFNN eliminates the errors by acting as the estimator for the tire nonlinearities. In another study, Wang et al (2019) proposed an SMC with an RBFNN for improving the tracking Steering angle from the lateral EMRAN 𝛿 𝑓 :…”

Robust EMRAN-aided Coupled Controller for Autonomous Vehicles

“…(email: sauranild@iisc.ac.in, vssuresh@iisc.ac.in) Narasimhan Sundararajan is with the School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore. (email: ensundara@ntu.edu.sg) A great deal of research efforts has been carried out in using learning-based methods for longitudinal control of AVs [9], [10], [11]. A neuro-fuzzy system that incorporates both the ride comfort and safety was demonstrated in [12] to keep the vehicle at a target speed.…”