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

Controlled execution of dynamic motions in quadrupedal robots, especiallythose with articulated soft bodies, presents a unique set of challenges thattraditional methods struggle to address efficiently. In this study, we tacklethese issues by relying on a simple yet effective two-stage learning frameworkto generate dynamic motions for quadrupedal robots. First, a gradient-freeevolution strategy is employed to discover simply represented control policies,eliminating the need for a predefined reference motion. Then, we refine thesepolicies using deep reinforcement learning. Our approach enables theacquisition of complex motions like pronking and back-flipping, effectivelyfrom scratch. Additionally, our method simplifies the traditionallylabour-intensive task of reward shaping, boosting the efficiency of thelearning process. Importantly, our framework proves particularly effective forarticulated soft quadrupeds, whose inherent compliance and adaptability makethem ideal for dynamic tasks but also introduce unique control challenges.

Two-Stage Learning of Highly Dynamic Motions with Rigid and Articulated Soft Quadrupeds