Visual Servoing from Deep Neural Networks

TL;DR

This paper introduces a deep learning-based visual servoing approach that achieves high-precision, robust, and real-time 6 DOF control by estimating relative pose from images, even under challenging conditions.

Contribution

It presents a novel dataset creation method and a neural network fine-tuning process for accurate pose estimation in visual servoing tasks.

Findings

Achieves less than 1mm positioning error in experiments

Robust convergence under lighting variations and occlusions

Real-time performance in 6 DOF robotic control

Abstract

We present a deep neural network-based method to perform high-precision, robust and real-time 6 DOF visual servoing. The paper describes how to create a dataset simulating various perturbations (occlusions and lighting conditions) from a single real-world image of the scene. A convolutional neural network is fine-tuned using this dataset to estimate the relative pose between two images of the same scene. The output of the network is then employed in a visual servoing control scheme. The method converges robustly even in difficult real-world settings with strong lighting variations and occlusions.A positioning error of less than one millimeter is obtained in experiments with a 6 DOF robot.