Maneuvers recognition system for laparoscopic surgery

Abstract

The work presented in this paper is focused on movement recognition as a first step to achieve the automation of a two-arm-surgical-robotic-system in the laparoscopic surgery environment. In order to accomplish coordination between the surgeon and the robotic assistant, a system able to recognize and differentiate between certain standard maneuvers should be developed. The new user interface is based on this maneuvers recognition system, which models the surgeon behavior. This interface consists of the data acquisition and the recognition system. The maneuvers are modeled with Hidden Markov Models (HMMs) and are trained off-line. The system has been tested in some in-vitro experiments as in tissue cutting, suturing and transporting.