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

We consider the problem of open-goal planning for robotic cloth manipulation.Core of our system is a neural network trained as a forward model of clothbehaviour under manipulation, with planning performed through backpropagation.We introduce a neural network-based routine for estimating mesh representationsfrom voxel input, and perform planning in mesh format internally. We addressthe problem of planning with incomplete domain knowledge by means of anexplicit epistemic uncertainty signal. This signal is calculated fromprediction divergence between two instances of the forward model network andused to avoid epistemic uncertainty during planning. Finally, we introducelogic for handling restriction of grasp points to a discrete set of candidates,in order to accommodate graspability constraints imposed by robotic hardware.We evaluate the system's mesh estimation, prediction, and planning ability onsimulated cloth for sequences of one to three manipulations. Comparativeexperiments confirm that planning on basis of estimated meshes improvesaccuracy compared to voxel-based planning, and that epistemic uncertaintyavoidance improves performance under conditions of incomplete domain knowledge.Planning time cost is a few seconds. We additionally present qualitativeresults on robot hardware.

Cloth Manipulation Planning on Basis of Mesh Representations with Incomplete Domain Knowledge and Voxel-to-Mesh Estimation