English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Localizing an object accurately with respect to a robot is a key step forautonomous robotic manipulation. In this work, we propose to tackle this taskknowing only 3D models of the robot and object in the particular case where thescene is viewed from uncalibrated cameras -- a situation which would be typicalin an uncontrolled environment, e.g., on a construction site. We demonstratethat this localization can be performed very accurately, with millimetricerrors, without using a single real image for training, a strong advantagesince acquiring representative training data is a long and expensive process.Our approach relies on a classification Convolutional Neural Network (CNN)trained using hundreds of thousands of synthetically rendered scenes withrandomized parameters. To evaluate our approach quantitatively and make itcomparable to alternative approaches, we build a new rich dataset of real robotimages with accurately localized blocks.

Virtual Training for a Real Application: Accurate Object-Robot Relative Localization without Calibration