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 present an approach to continuous perception for robotic laundry tasks.Our assumption is that the visual prediction of a garment's shapes and weightsis possible via a neural network that learns the dynamic changes of garmentsfrom video sequences. Continuous perception is leveraged during training byinputting consecutive frames, of which the network learns how a garmentdeforms. To evaluate our hypothesis, we captured a dataset of 40K RGB and 40Kdepth video sequences while a garment is being manipulated. We also conductedablation studies to understand whether the neural network learns the physicaland dynamic properties of garments. Our findings suggest that a modifiedAlexNet-LSTM architecture has the best classification performance for thegarment's shape and weights. To further provide evidence that continuousperception facilitates the prediction of the garment's shapes and weights, weevaluated our network on unseen video sequences and computed the 'MovingAverage' over a sequence of predictions. We found that our network has aclassification accuracy of 48% and 60% for shapes and weights of garments,respectively.

Continuous Perception for Classifying Shapes and Weights of Garmentsfor Robotic Vision Applications