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

Socially aware robots should be able, among others, to support fluenthuman-robot collaboration in tasks that require interdependent actions in orderto be solved. Towards enhancing mutual performance, collaborative robots shouldbe equipped with adaptation and learning capabilities. However, co-learning canbe a time consuming procedure. For this reason, transferring knowledge from anexpert could potentially boost the overall team performance. In the presentstudy, transfer learning was integrated in a deep Reinforcement Learning (dRL)agent. In a real-time and real-world set-up, two groups of participants had tocollaborate with a cobot under two different conditions of dRL agents; one thatwas transferring knowledge and one that did not. A probabilistic policy reusemethod was used for the transfer learning (TL). The results showed that therewas a significant difference between the performance of the two groups; TLhalved the time needed for the training of new participants to the task.Moreover, TL also affected the subjective performance of the teams and enhancedthe perceived fluency. Finally, in many cases the objective performance metricsdid not correlate with the subjective ones providing interesting insights aboutthe design of transparent and explainable cobot behaviour.

Enhancing team performance with transfer-learning during real-world human-robot collaboration