Task segmentation based on transition state clustering for surgical robot assistance

TL;DR

This paper introduces an online hierarchical transition state clustering method for surgical task segmentation, enabling effective robot assistance and improving task efficiency and cognitive workload in surgical training.

Contribution

It presents a novel hierarchical clustering framework for real-time surgical task segmentation using visual and kinematic data, enhancing robotic assistance capabilities.

Findings

High accuracy in transition segmentation

Fast computation time

Reduced task completion time and cognitive workload

Abstract

Understanding surgical tasks represents an important challenge for autonomy in surgical robotic systems. To achieve this, we propose an online task segmentation framework that uses hierarchical transition state clustering to activate predefined robot assistance. Our approach involves performing a first clustering on visual features and a subsequent clustering on robot kinematic features for each visual cluster. This enables to capture relevant task transition information on each modality independently. The approach is implemented for a pick-and-place task commonly found in surgical training. The validation of the transition segmentation showed high accuracy and fast computation time. We have integrated the transition recognition module with predefined robot-assisted tool positioning. The complete framework has shown benefits in reducing task completion time and cognitive workload.