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

Learning diverse skills is one of the main challenges in robotics. To thisend, imitation learning approaches have achieved impressive results. Thesemethods require explicitly labeled datasets or assume consistent skillexecution to enable learning and active control of individual behaviors, whichlimits their applicability. In this work, we propose a cooperative adversarialmethod for obtaining single versatile policies with controllable skill setsfrom unlabeled datasets containing diverse state transition patterns bymaximizing their discriminability. Moreover, we show that by utilizingunsupervised skill discovery in the generative adversarial imitation learningframework, novel and useful skills emerge with successful task fulfillment.Finally, the obtained versatile policies are tested on an agile quadruped robotcalled Solo 8 and present faithful replications of diverse skills encoded inthe demonstrations.

Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions