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

Being able to grasp objects is a fundamental component of most roboticmanipulation systems. In this paper, we present a new approach tosimultaneously reconstruct a mesh and a dense grasp quality map of an objectfrom a depth image. At the core of our approach is a novel camera-centricobject representation called the "object shell" which is composed of anobserved "entry image" and a predicted "exit image". We present animage-to-image residual ConvNet architecture in which the object shell and agrasp-quality map are predicted as separate output channels. The main advantageof the shell representation and the corresponding neural network architecture,ShellGrasp-Net, is that the input-output pixel correspondences in the shellrepresentation are explicitly represented in the architecture. We show thatthis coupling yields superior generalization capabilities for objectreconstruction and accurate grasp quality estimation implicitly considering theobject geometry. Our approach yields an efficient dense grasp quality map andan object geometry estimate in a single forward pass. Both of these outputs canbe used in a wide range of robotic manipulation applications. With rigorousexperimental validation, both in simulation and on a real setup, we show thatour shell-based method can be used to generate precise grasps and theassociated grasp quality with over 90% accuracy. Diverse grasps computed onshell reconstructions allow the robot to select and execute grasps in clutteredscenes with more than 93% success rate.

Simultaneous Object Reconstruction and Grasp Prediction using a Camera-centric Object Shell Representation