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

Using synthetic data for training deep neural networks for roboticmanipulation holds the promise of an almost unlimited amount of pre-labeledtraining data, generated safely out of harm's way. One of the key challenges ofsynthetic data, to date, has been to bridge the so-called reality gap, so thatnetworks trained on synthetic data operate correctly when exposed to real-worlddata. We explore the reality gap in the context of 6-DoF pose estimation ofknown objects from a single RGB image. We show that for this problem thereality gap can be successfully spanned by a simple combination of domainrandomized and photorealistic data. Using synthetic data generated in thismanner, we introduce a one-shot deep neural network that is able to performcompetitively against a state-of-the-art network trained on a combination ofreal and synthetic data. To our knowledge, this is the first deep networktrained only on synthetic data that is able to achieve state-of-the-artperformance on 6-DoF object pose estimation. Our network also generalizesbetter to novel environments including extreme lighting conditions, for whichwe show qualitative results. Using this network we demonstrate a real-timesystem estimating object poses with sufficient accuracy for real-world semanticgrasping of known household objects in clutter by a real robot.

Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objects