Markerless Suture Needle 6D Pose Tracking with Robust Uncertainty Estimation for Autonomous Minimally Invasive Robotic Surgery

TL;DR

This paper introduces a robust markerless 6D pose tracking method for suture needles in robotic surgery, utilizing uncertainty estimation and probabilistic fusion to improve localization accuracy over previous marker-based approaches.

Contribution

It presents a novel markerless tracking approach with uncertainty modeling and probabilistic fusion for autonomous suturing, outperforming prior marker-based methods.

Findings

Outperforms previous suture needle localization methods

Effective in autonomous regrasping and ex vivo environments

Robust to detection inconsistencies and occlusions

Abstract

Suture needle localization is necessary for autonomous suturing. Previous approaches in autonomous suturing often relied on fiducial markers rather than markerless detection schemes for localizing a suture needle due to the inconsistency of markerless detections. However, fiducial markers are not practical for real-world applications and can often be occluded from environmental factors in surgery (e.g., blood). Therefore in this work, we present a robust tracking approach for estimating the 6D pose of a suture needle when using inconsistent detections. We define observation models based on suture needles' geometry that captures the uncertainty of the detections and fuse them temporally in a probabilistic fashion. In our experiments, we compare different permutations of the observation models in the suture needle localization task to show their effectiveness. Our proposed method outperforms previous approaches in localizing a suture needle. We also demonstrate the proposed tracking method in an autonomous suture needle regrasping task and ex vivo environments.