Metaheuristic Algorithm for Automatic Cruise Control System

Accidents are less likely to happen when employing self-driving cars. However, automotive applications require more time and cost, simulation tool is a much more cost-effective and time-saving option. To reduce driver fatigue and ensure pedestrian safety, a vehicle’s cruise control depends heavily on control engineering. To aid in vehicle safety, the automotive manufacturing sector is forecast to develop a range of cruise control strategies. Because of elevated traffic on the roads, there is a significant need for the development of Automatic Cruise Control (ACC). The feedback control system’s architecture is essential for the achievement of ACC. This paper presents the controller tuning techniques for designing an ACC system. Researchers frequently utilized Ziegler-Nichols techniques in tuning Proportional Integral Derivative (PID) controllers. These tuning processes may be time-consuming and difficult for a complex nonlinear structure. This paper shows how to employ metaheuristic methodologies to quickly fine-tune the PID controller’s parameter. The first stage is to construct a mathematical model of the cruise control system on the vehicle. The PID settings are then optimized using the firefly and cuckoo search optimized algorithm. Both metaheuristic PID controllers achieve the necessary vehicle velocity, according to simulations. From the results, it also inferred that the designed controller helps the system to attain the required velocity smoothly, with negligible overshoot and minimal rise time.