Hardware simulation of lane keeping assist based on sensor fusion

Abstract

PurposeSafety is one of the most crucial factors in transportation due to so many factors, including human-error, that might result in various small to fatal accidents. This is why lane keeping assist (LKA) is an important system that needs to be developed. LKA will prevent the vehicle from moving to another lane because the driver is negligent to maintain the direction of the vehicle.Design/methodology/approachIn this study, LKA works using camera and ultrasonic sensors. The data coming from these two types of sensors are then fused to determine how should the car reacts to some certain situation so that it stays on the lane. The sensor fusion method was used to further ensure the car's safety.FindingsThe results of the hardware simulation show that LKA can successfully avoid the car from getting off the lane with safety index of 95% for high-speed mode and 100% for medium and low-speed mode; meanwhile on the use of ultrasonic sensor, the speed of the car is adjusted to the distance of the car's side disturbance.Originality/valueThis research has succeeded in simulating a sensor fusion–based LKA system.