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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Traditional approaches to quadruped control frequently employ simplified,hand-derived models. This significantly reduces the capability of the robotsince its effective kinematic range is curtailed. In addition, kinodynamicconstraints are often non-differentiable and difficult to implement in anoptimisation approach. In this work, these challenges are addressed by framingquadruped control as optimisation in a structured latent space. A deepgenerative model captures a statistical representation of feasible jointconfigurations, whilst complex dynamic and terminal constraints are expressedvia high-level, semantic indicators and represented by learned classifiersoperating upon the latent space. As a consequence, complex constraints arerendered differentiable and evaluated an order of magnitude faster thananalytical approaches. We validate the feasibility of locomotion trajectoriesoptimised using our approach both in simulation and on a real-world ANYmalquadruped. Our results demonstrate that this approach is capable of generatingsmooth and realisable trajectories. To the best of our knowledge, this is thefirst time latent space control has been successfully applied to a complex,real robot platform.

First Steps: Latent-Space Control with Semantic Constraints for Quadruped Locomotion