Visual servoing-based camera control for the da Vinci Surgical System

Abstract

Minimally Invasive Surgery (MIS)-which is a very beneficial technique to the patient but can be challenging to the surgeon-includes endoscopic camera handling by an assistant (traditional MIS) or a robotic arm under the control of the operator (Robot-Assisted MIS, RAMIS). Since in the case of RAMIS the endoscopic image is the sole sensory input, it is essential to keep the surgical tools in the field-of-view of the camera for patient safety reasons. Based on the endoscopic images, the movement of the endoscope holder arm can be automated by visual servoing techniques, which can reduce the risk of medical error. In this paper, we propose a marker-based visual servoing technique for automated camera positioning in the case of RAMIS. The method was validated on the research-enhanced da Vinci Surgical System. The implemented method is available at: https://github.com/ABC-iRobotics/irob-saf/tree/visua1_servoing.