Off-campus WSU users: To download campus access dissertations, please use the following link to log into our proxy server with your WSU access ID and password, then click the "Off-campus Download" button below.
Non-WSU users: Please talk to your librarian about requesting this thesis through interlibrary loan.
Access Type
WSU Access
Date of Award
January 2023
Degree Type
Thesis
Degree Name
M.S.
Department
Computer Science
First Advisor
Abhilash Pandya
Abstract
Augmented reality for surgical robots offers the surgeon a powerful user interface when planning and executing a procedure, however, it is challenging due to smaller cameras and lower tolerance for error. This thesis uses a dense neural network to reduce the total projection error by directly learning the mapping of a 3-dimensional point to a 2-dimensional image plane. A curated dataset was collected, labelled, and cleaned which was then used to train the network. The model was then evaluated on approximately 2000 data points. The results show a median error of 7 pixels when using a neural network as compared to an error of 50 pixels when using a more traditional approach involving camera calibration and robot kinematics. The pixel error was then converted to error in millimeters, resulting in an error of 1.4mm. This work is a step towards achieving sub-millimeter accuracy for AR in surgical robots.
Recommended Citation
Shankar, Abhishek, "An Ai Approach To Markerless Augmented Reality For The Da Vinci Surgical Robot" (2023). Wayne State University Theses. 919.
https://digitalcommons.wayne.edu/oa_theses/919