Introduction: We have developed an autonomous vehicle that utilizes computer vision to achieve lane-keeping and stop-sign detection on a small track for our Mobile and Embedded Systems course. The vehicle converts images from the camera into an HSV color space to detect colors and line segments used to determine when to rotate or stop movement. Lastly, the vehicle utilizes a PID control system to provide constant feedback to the car to constantly check for errors and compensate for them by adjusting motor speeds and steering angles. Our implementation of the autonomous vehicle draws significantly from the following Instructable:
User raja_961, “Autonomous Lane-Keeping Car Using RaspberryPi and OpenCV”. Instructables. URL:https://www.instructables.com/Autonomous-Lane-Keeping-Car-Using-Raspberry-Pi-and/
StopSignApproach: For the vehicle to stop when detecting a stop sign, our car assigns a threshold of RGB values in the HSV color space to see when an object in its sight is red. When our RGB threshold for the stop sign in the vehicle's camera is satisfied, the PID control system provides appropriate feedback to the car such that the wheel's motors stop. After 3 seconds, the PID control system then provides updated input to the wheel's motor controllers to start moving again at its appropriate speed.