Neural Network Based Sliding Mode Lateral Control For Autonomous Vehicle

Lhoussain El Hajjami, El Mehdi Mellouli, Mohammed Berrada

20202020 1st International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET)24 citationsDOI

Abstract

Nowadays, autonomous driving represents a major challenge for automobile manufacturers in order to reach the latest levels of autonomy. Any autonomous vehicle development project focuses on three fundamental phases; environmental perception, trajectory planning and path pursuit which including control and command as an integral part. This paper presents a modified Sliding Mode Controller based on the Radial Basic Function Neural Networks (SMC_RBNN) able to control the lateral dynamics of the vehicle. For a sinusoidal reference path, the proposed control strategy, SMC_RBNN, showed better results than those obtained with a conventional Sliding Mode Controller (SMC), in terms of lateral tracking error.

Topics & Concepts

Control theory (sociology)TrajectoryController (irrigation)Sliding mode controlArtificial neural networkMode (computer interface)Path (computing)Computer scienceControl (management)Tracking (education)Control engineeringVehicle dynamicsEngineeringArtificial intelligenceAutomotive engineeringNonlinear systemPhysicsOperating systemBiologyAgronomyAstronomyPedagogyPsychologyQuantum mechanicsProgramming languageVehicle Dynamics and Control SystemsAutonomous Vehicle Technology and SafetyReal-time simulation and control systems