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

Most of industrial robotic assembly tasks today require fixed initialconditions for successful assembly. These constraints induce high productioncosts and low adaptability to new tasks. In this work we aim towards flexibleand adaptable robotic assembly by using 3D CAD models for all parts to beassembled. We focus on a generic assembly task - the Siemens InnovationChallenge - in which a robot needs to assemble a gear-like mechanism with highprecision into an operating system. To obtain the millimeter-accuracy requiredfor this task and industrial settings alike, we use a depth camera mounted nearthe robot end-effector. We present a high-accuracy two-stage pose estimationprocedure based on deep convolutional neural networks, which includesdetection, pose estimation, refinement, and handling of near- and fullsymmetries of parts. The networks are trained on simulated depth images withmeans to ensure successful transfer to the real robot. We obtain an averagepose estimation error of 2.16 millimeters and 0.64 degree leading to 91%success rate for robotic assembly of randomly distributed parts. To the best ofour knowledge, this is the first time that the Siemens Innovation Challenge isfully addressed, with all the parts assembled with high success rates.

Learning Pose Estimation for High-Precision Robotic Assembly Using Simulated Depth Images