PCA-Based Visual Servoing Using Optical Coherence Tomography

Abstract

This article deals with the development of a vision-based control law to achieve high-accuracy automatic six degrees of freedom (DoF) positioning tasks. The objective of this work is to be able to replace a biological sample under an optical device for a non-invasive depth examination at any given time (i.e., performing repetitive and accurate optical characterizations of the sample). The optical examination, also called optical biopsy, is performed thanks to an optical coherence tomography (OCT) system. The OCT device is used to perform a 3-dimensional optical biopsy, and as a sensor to control the robot motion during the repositioning process. The proposed visual servoing controller uses the 3D pose of the studied biological sample estimated directly from the C-scan OCT images using a Principal Component Analysis (PCA) framework. The proposed materials and methods were experimentally validated using a spectral-domain OCT and a 6-DoF robotic platform. The obtained results have demonstrated the pertinence of such methods which offer a positioning accuracy around 0.052 ± 0.03 mm (mean error ± standard deviation) for linear errors and 0.41 ± 0.16 • for angular ones over a 8 × 9 × 3.5 mm 3 workspace.

3D Spectral Domain Registration-Based Visual Servoing

“…Most of the aforementioned state of the art on visual servoing is based on 2D image information and the literature using 3D data for visual servoing, e.g., depth maps or point clouds, is very much limited. Very few recent works have reported such methods [16]- [18]. A particular advantage of using 3D data over 2D images is that they are well-suited for complex environments, i.e., texture-less, varying light, unstructured etc., and avoid computation of complex pose estimations.…”