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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Dense Object Nets (DONs) by Florence, Manuelli and Tedrake (2018) introduceddense object descriptors as a novel visual object representation for therobotics community. It is suitable for many applications including objectgrasping, policy learning, etc. DONs map an RGB image depicting an object intoa descriptor space image, which implicitly encodes key features of an objectinvariant to the relative camera pose. Impressively, the self-supervisedtraining of DONs can be applied to arbitrary objects and can be evaluated anddeployed within hours. However, the training approach relies on accurate depthimages and faces challenges with small, reflective objects, typical forindustrial settings, when using consumer grade depth cameras. In this paper weshow that given a 3D model of an object, we can generate its descriptor spaceimage, which allows for supervised training of DONs. We rely on LaplacianEigenmaps (LE) to embed the 3D model of an object into an optimally generatedspace. While our approach uses more domain knowledge, it can be efficientlyapplied even for smaller and reflective objects, as it does not rely on depthinformation. We compare the training methods on generating 6D grasps forindustrial objects and show that our novel supervised training approachimproves the pick-and-place performance in industry-relevant tasks.

Supervised Training of Dense Object Nets using Optimal Descriptors for Industrial Robotic Applications