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 this paper we introduce a novel framework for expressing and learningforce-sensitive robot manipulation skills. It is based on a formalism thatextends our previous work on adaptive impedance control with meta parameterlearning and compatible skill specifications. This way the system is also ableto make use of abstract expert knowledge by incorporating process descriptionsand quality evaluation metrics. We evaluate various state-of-the-art schemesfor the meta parameter learning and experimentally compare selected ones. Ourresults clearly indicate that the combination of our adaptive impedancecontroller with a carefully defined skill formalism significantly reduces thecomplexity of manipulation tasks even for learning peg-in-hole withsubmillimeter industrial tolerances. Overall, the considered system is able tolearn variations of this skill in under 20 minutes. In fact, experimentally thesystem was able to perform the learned tasks faster than humans, leading to thefirst learning-based solution of complex assembly at such real-worldperformance.

A Framework for Robot Manipulation: Skill Formalism, Meta Learning and Adaptive Control