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

In real-world environments, robots need to be resilient to damages and robustto unforeseen scenarios. Quality-Diversity (QD) algorithms have beensuccessfully used to make robots adapt to damages in seconds by leveraging adiverse set of learned skills. A high diversity of skills increases the chancesof a robot to succeed at overcoming new situations since there are morepotential alternatives to solve a new task.However, finding and storing a largebehavioural diversity of multiple skills often leads to an increase incomputational complexity. Furthermore, robot planning in a large skill space isan additional challenge that arises with an increased number of skills.Hierarchical structures can help reducing this search and storage complexity bybreaking down skills into primitive skills. In this paper, we introduce theHierarchical Trial and Error algorithm, which uses a hierarchical behaviouralrepertoire to learn diverse skills and leverages them to make the robot adaptquickly in the physical world. We show that the hierarchical decomposition ofskills enables the robot to learn more complex behaviours while keeping thelearning of the repertoire tractable. Experiments with a hexapod robot showthat our method solves a maze navigation tasks with 20% less actions insimulation, and 43% less actions in the physical world, for the mostchallenging scenarios than the best baselines while having 78% less completefailures.

Online Damage Recovery for Physical Robots with Hierarchical Quality-Diversity