Visual Servoing in Autoencoder Latent Space
- 21 January 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 3234-3241
Abstract
Visual servoing (VS) is a common way in robotics to control a robot motion usinginformation acquired by a camera. This approach requires to extract visual information from the image to design the control law. The resulting servo loop is built in order to minimize an error expressed in the image space. We consider a direct visual servoing (DVS) from whole images. We propose a new framework to perform VS in the latent space learned by a convolutional autoencoder. We show that this latent space avoids explicit feature extraction and tracking issues and provides a good representation, smoothing the cost function of the VS process. Besides, our experiments show that this unsupervised learning approach allows us to obtain, without labelling cost, an accurate end-positioning, often on par with the best DVS methods in terms of accuracy but with a larger convergence area.Keywords
This publication has 23 references indexed in Scilit:
- Stable reinforcement learning with autoencoders for tactile and visual data2016
- Deep Residual Learning for Image Recognition2016
- Deep spatial autoencoders for visuomotor learning2016
- FlowNet: Learning Optical Flow with Convolutional Networks2015
- PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Representation Learning: A Review and New PerspectivesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Learn to Swing Up and Balance a Real Pole Based on Raw Visual Input Data2012
- Control Camera and Light Source Positions using Image Gradient Information2007
- Reducing the Dimensionality of Data with Neural NetworksScience, 2006