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

The world around us is full of soft objects we perceive and deform withdexterous hand movements. For a robotic hand to control soft objects, it has toacquire online state feedback of the deforming object. While RGB-D cameras cancollect occluded point clouds at a rate of 30Hz, this does not represent acontinuously trackable object surface. Hence, in this work, we developed amethod that takes as input a template mesh which is the mesh of an object inits non-deformed state and a deformed point cloud of the same object, and thenshapes the template mesh such that it matches the deformed point cloud. Thereconstruction of meshes from point clouds has long been studied in the fieldof Computer graphics under 3D reconstruction and 4D reconstruction, however,both lack the speed and generalizability needed for robotics applications. Ourmodel is designed using a point cloud auto-encoder and a Real-NVP architecture.Our trained model can perform mesh reconstruction and tracking at a rate of58Hz on a template mesh of 3000 vertices and a deformed point cloud of 5000points and is generalizable to the deformations of six different objectcategories which are assumed to be made of soft material in our experiments(scissors, hammer, foam brick, cleanser bottle, orange, and dice). The objectmeshes are taken from the YCB benchmark dataset. An instance of a downstreamapplication can be the control algorithm for a robotic hand that requiresonline feedback from the state of the manipulated object which would allowonline grasp adaptation in a closed-loop manner. Furthermore, the trackingcapacity of our method can help in the system identification of deformingobjects in a marker-free approach. In future work, we will extend our trainedmodel to generalize beyond six object categories and additionally to real-worlddeforming point clouds.

Fast Point Cloud to Mesh Reconstruction for Deformable Object Tracking