Approach for modelling and controlling of autonomous cruise control system through machine learning algorithms

Abstract

Automated cruise control installation is one of the utmost significant phases in the auto industry's pursuit of autonomous vehicles. The controller of choice is one of the key factors in determining whether a design will be durable and cost-effective. The model-based controller and a cutting-edge algorithmic optimization method are both presented inside the framework of this proposed study. The suggested controller may achieve the desired characteristics of the design, including a faster rise time, a faster settle time, a smaller peak overshoot, and a smaller steady-state error. A MATLAB-executed and -simulated system model using a control method based on a hybrid genetic algorithm and reinforcement learning has been used to effectively and automatically regulate the vehicle's velocity in compliance with all design parameters.