Fuzzy-based intelligent control strategy for a person following robot

This paper presents a fuzzy-based intelligent control strategy allowing a mobile robot to safely follow a given person. The robot is embedded with two sensors: a RFID and a stereo camera. The RFID can locate the given person with an ID tag, and the stereo camera can be used to detect the target. Based on the two sensors, a robust control strategy is designed according to the target´s speed and his distance from the robot. The strategy consists of two fuzzy controllers. The first is a fuzzy based reference linear velocity adjustment controller, and the other is a fuzzy based turning-gain adjustment controller. Up to the results from the two controllers, the robot´s left wheel velocity and right wheel velocity are adaptively varied for driving the robot towards the target as soon as possible. Moreover, the RFID can provide a wider field of view (FOV) than the camera. If the person turns out of the FOV of the camera, the control strategy will drive the robot towards the target according to the information from RFID as soon as possible. Finally, the algorithm is evaluated on the Pioeer3-DX, and it shows that the presented algorithm can follow the target robustly.