Modelling, Simulation and Virtual validation of Adaptive Cruise Control (ACC) Algorithm based on Sensor Fusion

Abstract

Adaptive Cruise Control (ACC) systems are rapidly becoming an integral part of modern vehicles, contributing to both enhanced driving comfort and increased road safety. Traditional approaches for ACC often rely on a single type of sensor, which could be limiting in dynamically evolving driving scenarios. To improve the system's performance in such complex driving conditions, an enhanced approach using Sensor fusion technique has been discussed. Further, based on the detections the Most Important Object (MIO) lead car is obtained, with which a robust stateful control algorithm determines the appropriate set speed for the Ego vehicle to maintain safe distance with the preceding (lead car) in the same lane, based on the states of Ego and Lead vehicle. This set speed of the Ego Vehicle is maintained by a Vehicle Longitudinal controller. The modelled system has been validated in a closed-loop Virtual Environment with custom scenarios for intricate analysis of system performance.