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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Collaborative robots are becoming more common on factory floors as well asregular environments, however, their safety still is not a fully solved issue.Collision detection does not always perform as expected and collision avoidanceis still an active research area. Collision avoidance works well for fixedrobot-camera setups, however, if they are shifted around, Eye-to-Handcalibration becomes invalid making it difficult to accurately run many of theexisting collision avoidance algorithms. We approach the problem by presentinga stand-alone system capable of detecting the robot and estimating itsposition, including individual joints, by using a simple 2D colour image as aninput, where no Eye-to-Hand calibration is needed. As an extension of previouswork, a two-stage transfer learning approach is used to re-train amulti-objective convolutional neural network (CNN) to allow it to be used withheterogeneous robot arms. Our method is capable of detecting the robot inreal-time and new robot types can be added by having significantly smallertraining datasets compared to the requirements of a fully trained network. Wepresent data collection approach, the structure of the multi-objective CNN, thetwo-stage transfer learning training and test results by using real robots fromUniversal Robots, Kuka, and Franka Emika. Eventually, we analyse possibleapplication areas of our method together with the possible improvements.

Two-Stage Transfer Learning for Heterogeneous Robot Detection and 3D Joint Position Estimation in a 2D Camera Image using CNN