The paper proposes design concepts of a vision-based shopping assistant robot which can serve people in a mall. By using such robots, a mall could not only save human resources effectively but also improve the quality of information service. In general, a mall always provides three kinds of customer services as guiding, communication and accompanying. In this paper, a fuzzy collision-free guiding controller and a fuzzy following controller are proposed for guiding and accompanying services respectively. For collision-free controls, a named "warning area" will be preplanned in the image plane to check whether there are objectives and/or obstacles in front of the robot. Besides, the eigenblock of objectives could be determined by using color image processing methods. The color recognition and size filter are used to search for proper objective image blocks and their relative locations. Based on a fuzzy following controller, the robot will accomplish the mobility of following the specified customer. Several experiments demonstrate the feasibility of the proposed robotic system.