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

Applications in fields ranging from home care to warehouse fulfillment tosurgical assistance require robots to reliably manipulate the shape of 3Ddeformable objects. Analytic models of elastic, 3D deformable objects requirenumerous parameters to describe the potentially infinite degrees of freedompresent in determining the object's shape. Previous attempts at performing 3Dshape control rely on hand-crafted features to represent the object shape andrequire training of object-specific control models. We overcome these issuesthrough the use of our novel DeformerNet neural network architecture, whichoperates on a partial-view point cloud of the manipulated object and a pointcloud of the goal shape to learn a low-dimensional representation of the objectshape. This shape embedding enables the robot to learn a visual servocontroller that computes the desired robot end-effector action to iterativelydeform the object toward the target shape. We demonstrate both in simulationand on a physical robot that DeformerNet reliably generalizes to object shapesand material stiffness not seen during training. Crucially, using DeformerNet,the robot successfully accomplishes three surgical sub-tasks: retraction(moving tissue aside to access a site underneath it), tissue wrapping (asub-task in procedures like aortic stent placements), and connecting twotubular pieces of tissue (a sub-task in anastomosis).

DeformerNet: Learning Bimanual Manipulation of 3D Deformable Objects