This paper presents an image-based cooperative driving system for telepresence robot, which allows safe operation in indoor environments and is meant to minimize the burden on novice users operating the robot. The paper focuses on one emerging telepresence robot, namely, mobile remote presence systems for social interaction. Such systems brings new opportunities for applications in healthcare and elderly care by allowing caregivers to communicate with patients and elderly from remote locations. However, using such systems can be a difficult task particularly for caregivers without proper training. The paper presents a first implementation of a vision-based cooperative driving enhancement to a telepresence robot. A preliminary evaluation in the laboratory environment is presented.