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

Robotic manipulation tasks, such as wiping with a soft sponge, requirecontrol from multiple rich sensory modalities. Human-robot interaction, aimedat teaching robots, is difficult in this setting as there is potential formismatch between human and machine comprehension of the rich data streams. Wetreat the task of interpretable learning from demonstration as an optimisationproblem over a probabilistic generative model. To account for thehigh-dimensionality of the data, a high-capacity neural network is chosen torepresent the model. The latent variables in this model are explicitly alignedwith high-level notions and concepts that are manifested in a set ofdemonstrations. We show that such alignment is best achieved through the use oflabels from the end user, in an appropriately restricted vocabulary, incontrast to the conventional approach of the designer picking a prior over thelatent variables. Our approach is evaluated in the context of two table-toprobot manipulation tasks performed by a PR2 robot -- that of dabbing liquidswith a sponge (forcefully pressing a sponge and moving it along a surface) andpouring between different containers. The robot provides visual information,arm joint positions and arm joint efforts. We have made videos of the tasks anddata available - see supplementary materials at:https://sites.google.com/view/weak-label-lfd.

Learning from Demonstration with Weakly Supervised Disentanglement