A Robotic Recording and Playback Platform for Training Surgeons and Learning Autonomous Behaviors Using the da Vinci Surgical System

Abstract

This paper describes a recording and playback system developed using a da Vinci Standard Surgical System and research kit. The system records stereo laparoscopic videos, robot arm joint angles, and surgeon⁻console interactions in a synchronized manner. A user can then, on-demand and at adjustable speeds, watch stereo videos and feel recorded movements on the hand controllers of entire procedures or sub procedures. Currently, there is no reported comprehensive ability to capture expert surgeon movements and insights and reproduce them on hardware directly. This system has important applications in several areas: (1) training of surgeons, (2) collection of learning data for the development of advanced control algorithms and intelligent autonomous behaviors, and (3) use as a “black box„ for retrospective error analysis. We show a prototype of such an immersive system on a clinically-relevant platform along with its recording and playback fidelity. Lastly, we convey possible research avenues to create better systems for training and assisting robotic surgeons.

Keywords

• robotic surgery
• surgical training
• machine learning
• surgical automation