Image-based fuzzy control of a car-like mobile robot for parking problems

The image-based control method can operate a mobile robot by controlling only image information acquired from camera images without using the robot states. This paper is devoted to design a car-like mobile robot that possesses autonomous angle parking and perpendicular parking capability by using an image-based fuzzy controller. A parking frame which is drawn on the floor is detected by a robot that is equipped with a camera. For both parking types, the desired target line to be followed by the robot is generated by calculating the image features which are extracted from the captured image. The fuzzy controller is designed with a reasoning mechanism composed of two inputs, which are the slope and intercept of the target line, and one output that is the steering angle of the robot. Simulation results illustrate the effectiveness of the proposed method.