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

Learning from Demonstration (LfD) constitutes one of the most robustmethodologies for constructing efficient cognitive robotic systems. Despite thelarge body of research works already reported, current key technologicalchallenges include those of multi-agent learning and long-term autonomy.Towards this direction, a novel cognitive architecture for multi-agent LfDrobotic learning is introduced, targeting to enable the reliable deployment ofopen, scalable and expandable robotic systems in large-scale and complexenvironments. In particular, the designed architecture capitalizes on therecent advances in the Artificial Intelligence (AI) field, by establishing aFederated Learning (FL)-based framework for incarnating a multi-humanmulti-robot collaborative learning environment. The fundamentalconceptualization relies on employing multiple AI-empowered cognitive processes(implementing various robotic tasks) that operate at the edge nodes of anetwork of robotic platforms, while global AI models (underpinning theaforementioned robotic tasks) are collectively created and shared among thenetwork, by elegantly combining information from a large number of human-robotinteraction instances. Regarding pivotal novelties, the designed cognitivearchitecture a) introduces a new FL-based formalism that extends theconventional LfD learning paradigm to support large-scale multi-agentoperational settings, b) elaborates previous FL-based self-learning roboticschemes so as to incorporate the human in the learning loop and c) consolidatesthe fundamental principles of FL with additional sophisticated AI-enabledlearning methodologies for modelling the multi-level inter-dependencies amongthe robotic tasks. The applicability of the proposed framework is explainedusing an example of a real-world industrial case study for agileproduction-based Critical Raw Materials (CRM) recovery.

Towards open and expandable cognitive AI architectures for large-scale multi-agent human-robot collaborative learning