Open Collections

Eye gaze tracking in surgical robotics

University of British Columbia

Robot-assisted surgery allows surgeons to have improved control and visualization in minimally invasive procedures. Eye gaze tracking is a valuable tool for studying and improving the surgeon experience during robot-assisted surgery. Eye gaze information gives insight on how surgeons are interacting with surgical systems as well as their intentions during surgical tasks. This thesis describes the development of an eye gaze tracker for the da Vinci Surgical System. The eye gaze tracker is designed to track both the 2D and 3D eye gaze of a surgeon. It interfaces with the da Vinci Surgical System through the da Vinci Research Kit (dVRK) and Robot Operating System (ROS) frameworks. The use of the eye gaze tracker is demonstrated in two applications. Firstly, a motor control framework is designed to aid surgeons in moving surgical tools towards their point of gaze. A haptic force is applied to the da Vinci master manipulators to pull the surgeon's hands towards where they are looking. This framework is demonstrated on a full da Vinci Surgical System on dry lab tasks. Secondly, eye gaze information is collected from 7 surgeons performing realistic clinical tasks with the da Vinci Surgical System. A prediction model using a random forest classifier is built based on the eye gaze information and tool kinematic information in order to predict how and when surgeons move their camera. This behavioural model has applications in both surgeon training and endoscope automation.

Text

2017-08-28

Attribution-NonCommercial-NoDerivatives 4.0 International

http://hdl.handle.net/2429/62845

Biomedical Engineering

University of British Columbia

UBCV

http://creativecommons.org/licenses/by-nc-nd/4.0/