Nonlinear Dynamic Control of Autonomous Vehicle Under Slip Using Improved Backpropagation Algorithm

International Journal of Research and Innovation in Applied Science (IJRIAS) | Volume VI, Issue IX, September 2021|ISSN 2454-6194

Nonlinear Dynamic Control of Autonomous Vehicle Under Slip Using Improved Backpropagation Algorithm

Harbor M.C¹, Eneh I. I², Ebere U.C^3
1,²Enugu State University of Science and Technology, Enugu, Nigeria
³Destinet Smart Technologies, Enugu Nigeria

Abstract: This paper presents the nonlinear dynamic control of autonomous vehicle under slip using improved back propagation algorithm. The aim is to address the issue of nonlinearity experienced in autonomous vehicle under translational state due to slip force. This was achieved developing a nonlinear vehicle dynamic model under slip, improved model of the training algorithm, slip dataset, feature extraction model and the control model. The work was implemented using simulink and tested using the necessary simulation parameters. The result was evaluated using a regression analysis with predictive accuracy of 99.5%, and control response time of 0.005sec.

Keywords: back-propagation, autonomous vehicle, slip, regression, control response

I.INTRODUCTION

According to [1] Autonomous vehicle (AV) is a vehicle capable of navigating District roadways and interpreting traffic-control devices without a driver actively operating any of the vehicle’s control systems. They are vehicle designed with automated systems to provide electronic blind-spot assistance, crash avoidance, emergency braking, parking assistance, adaptive cruise control, lane-keep assistance, lane-departure warning, or traffic-jam and queuing assistance [1]. These features are embedded in the system (AV) to ensure controllability, reliability, confidence, accuracy and safety during motion. However certain factors like road frictional coefficients slip force, poor automatic brake system response, poor controller response, aggressive nature of servomotors, mechanical faults, rigid power steering among others, stand in the way of realizing this goals completely and as a result causes non linear vehicle dynamics during translation.
In recent times various methodologies have been adopted to ensure that these challenges can be eradicated, such includes the implementation of intelligent tires using accelerometers [2], smart systems for vital signs and vehicle stress condition monitoring [3], the use of intelligent slip estimation controllers [3] [1], among other techniques to mention a few. However despite the success they achieved, one will ask why is it that a complete control of AV is yet to be achieved?
According to [4] the major challenges of autonomous cruise control is that some factors that affects its stability like slip and road coefficients are inevitable. Once a vehicle is in motion, slip force will continue to act on the tires at a rate

Read More