AI Lifecycle Zero-Touch Orchestration within the Edge-to-Cloud Continuum for Industry 5.0

Enrico Alberti; Sergio Alvarez-Napagao; Victor Anaya; Marta Barroso; Cristian Barrué; Christian Beecks; Letizia Bergamasco; Sisay Adugna Chala; Victor Gimenez-Abalos; Alexander Graß; Daniel Hinjos; Maike Holtkemper; Natalia Jakubiak; Alexandros Nizamis; Edoardo Pristeri; Miquel  Sànchez-Marrè; Georg Schlake; Jona Scholz; Gabriele Scivoletto; Stefan Walter

doi:10.3390/systems12020048

AI Lifecycle Zero-Touch Orchestration within the Edge-to-Cloud Continuum for Industry 5.0

Enrico Alberti
, Sergio Alvarez-Napagao
, Victor Anaya
, Marta Barroso
, Cristian Barrué
, Christian Beecks
, Letizia Bergamasco
, Sisay Adugna Chala
, Victor Gimenez-Abalos
, Alexander Graß
, Daniel Hinjos
, Maike Holtkemper
, Natalia Jakubiak
, Alexandros Nizamis
, Edoardo Pristeri
, Miquel Sànchez-Marrè
, Georg Schlake
, Jona Scholz
, Gabriele Scivoletto
, Stefan Walter^*

^*Corresponding author for this work

BA5609 Intelligent supply chains and logistics

Research output: Contribution to journal › Article › Scientific › peer-review

14 Citations (Scopus)

212 Downloads (Pure)

Abstract

The advancements in human-centered artificial intelligence (HCAI) systems for Industry 5.0 is a new phase of industrialization that places the worker at the center of the production process and uses new technologies to increase prosperity beyond jobs and growth. HCAI presents new objectives that were unreachable by either humans or machines alone, but this also comes with a new set of challenges. Our proposed method accomplishes this through the knowlEdge architecture, which enables human operators to implement AI solutions using a zero-touch framework. It relies on containerized AI model training and execution, supported by a robust data pipeline and rounded off with human feedback and evaluation interfaces. The result is a platform built from a number of components, spanning all major areas of the AI lifecycle. We outline both the architectural concepts and implementation guidelines and explain how they advance HCAI systems and Industry 5.0. In this article, we address the problems we encountered while implementing the ideas within the edge-to-cloud continuum. Further improvements to our approach may enhance the use of AI in Industry 5.0 and strengthen trust in AI systems.

Original language	English
Article number	48
Journal	Systems
Volume	12
Issue number	2
DOIs	https://doi.org/10.3390/systems12020048
Publication status	Published - 2 Feb 2024
MoE publication type	A1 Journal article-refereed

Funding

The research leading to these results has received funding from Horizon 2020 and the European Union’s Framework Programme for Research and Innovation (H2020/2014-2020) under grant agreement no. 957331.

Keywords

digital twin
human-centered AI
Industry 4.0
manufacturing
model orchestration

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.3390/systems12020048Licence: CC BY

systems12020048Final published version, 2.79 MBLicence: CC BY

Cite this

Alberti, E., Alvarez-Napagao , S., Anaya, V., Barroso, M., Barrué, C., Beecks, C., Bergamasco, L., Chala, S. A., Gimenez-Abalos, V., Graß, A., Hinjos, D., Holtkemper, M., Jakubiak, N., Nizamis, A., Pristeri, E., Sànchez-Marrè, M., Schlake, G., Scholz, J., Scivoletto, G., & Walter, S. (2024). AI Lifecycle Zero-Touch Orchestration within the Edge-to-Cloud Continuum for Industry 5.0. Systems, 12(2), Article 48. https://doi.org/10.3390/systems12020048

@article{5580db00c95649f1829fcacda9ac6cac,

title = "AI Lifecycle Zero-Touch Orchestration within the Edge-to-Cloud Continuum for Industry 5.0",

abstract = "The advancements in human-centered artificial intelligence (HCAI) systems for Industry 5.0 is a new phase of industrialization that places the worker at the center of the production process and uses new technologies to increase prosperity beyond jobs and growth. HCAI presents new objectives that were unreachable by either humans or machines alone, but this also comes with a new set of challenges. Our proposed method accomplishes this through the knowlEdge architecture, which enables human operators to implement AI solutions using a zero-touch framework. It relies on containerized AI model training and execution, supported by a robust data pipeline and rounded off with human feedback and evaluation interfaces. The result is a platform built from a number of components, spanning all major areas of the AI lifecycle. We outline both the architectural concepts and implementation guidelines and explain how they advance HCAI systems and Industry 5.0. In this article, we address the problems we encountered while implementing the ideas within the edge-to-cloud continuum. Further improvements to our approach may enhance the use of AI in Industry 5.0 and strengthen trust in AI systems.",

keywords = "digital twin, human-centered AI, Industry 4.0, manufacturing, model orchestration",

author = "Enrico Alberti and Sergio Alvarez-Napagao and Victor Anaya and Marta Barroso and Cristian Barru{\'e} and Christian Beecks and Letizia Bergamasco and Chala, \{Sisay Adugna\} and Victor Gimenez-Abalos and Alexander Gra{\ss} and Daniel Hinjos and Maike Holtkemper and Natalia Jakubiak and Alexandros Nizamis and Edoardo Pristeri and Miquel S{\`a}nchez-Marr{\`e} and Georg Schlake and Jona Scholz and Gabriele Scivoletto and Stefan Walter",

year = "2024",

month = feb,

day = "2",

doi = "10.3390/systems12020048",

language = "English",

volume = "12",

journal = "Systems",

issn = "2079-8954",

publisher = "MDPI",

number = "2",

}

Alberti, E, Alvarez-Napagao , S, Anaya, V, Barroso, M, Barrué, C, Beecks, C, Bergamasco, L, Chala, SA, Gimenez-Abalos, V, Graß, A, Hinjos, D, Holtkemper, M, Jakubiak, N, Nizamis, A, Pristeri, E, Sànchez-Marrè, M, Schlake, G, Scholz, J, Scivoletto, G & Walter, S 2024, 'AI Lifecycle Zero-Touch Orchestration within the Edge-to-Cloud Continuum for Industry 5.0', Systems, vol. 12, no. 2, 48. https://doi.org/10.3390/systems12020048

TY - JOUR

T1 - AI Lifecycle Zero-Touch Orchestration within the Edge-to-Cloud Continuum for Industry 5.0

AU - Alberti, Enrico

AU - Alvarez-Napagao , Sergio

AU - Anaya, Victor

AU - Barroso, Marta

AU - Barrué, Cristian

AU - Beecks, Christian

AU - Bergamasco, Letizia

AU - Chala, Sisay Adugna

AU - Gimenez-Abalos, Victor

AU - Graß, Alexander

AU - Hinjos, Daniel

AU - Holtkemper, Maike

AU - Jakubiak, Natalia

AU - Nizamis, Alexandros

AU - Pristeri, Edoardo

AU - Sànchez-Marrè, Miquel

AU - Schlake, Georg

AU - Scholz, Jona

AU - Scivoletto, Gabriele

AU - Walter, Stefan

PY - 2024/2/2

Y1 - 2024/2/2

N2 - The advancements in human-centered artificial intelligence (HCAI) systems for Industry 5.0 is a new phase of industrialization that places the worker at the center of the production process and uses new technologies to increase prosperity beyond jobs and growth. HCAI presents new objectives that were unreachable by either humans or machines alone, but this also comes with a new set of challenges. Our proposed method accomplishes this through the knowlEdge architecture, which enables human operators to implement AI solutions using a zero-touch framework. It relies on containerized AI model training and execution, supported by a robust data pipeline and rounded off with human feedback and evaluation interfaces. The result is a platform built from a number of components, spanning all major areas of the AI lifecycle. We outline both the architectural concepts and implementation guidelines and explain how they advance HCAI systems and Industry 5.0. In this article, we address the problems we encountered while implementing the ideas within the edge-to-cloud continuum. Further improvements to our approach may enhance the use of AI in Industry 5.0 and strengthen trust in AI systems.

AB - The advancements in human-centered artificial intelligence (HCAI) systems for Industry 5.0 is a new phase of industrialization that places the worker at the center of the production process and uses new technologies to increase prosperity beyond jobs and growth. HCAI presents new objectives that were unreachable by either humans or machines alone, but this also comes with a new set of challenges. Our proposed method accomplishes this through the knowlEdge architecture, which enables human operators to implement AI solutions using a zero-touch framework. It relies on containerized AI model training and execution, supported by a robust data pipeline and rounded off with human feedback and evaluation interfaces. The result is a platform built from a number of components, spanning all major areas of the AI lifecycle. We outline both the architectural concepts and implementation guidelines and explain how they advance HCAI systems and Industry 5.0. In this article, we address the problems we encountered while implementing the ideas within the edge-to-cloud continuum. Further improvements to our approach may enhance the use of AI in Industry 5.0 and strengthen trust in AI systems.

KW - digital twin

KW - human-centered AI

KW - Industry 4.0

KW - manufacturing

KW - model orchestration

UR - https://www.scopus.com/pages/publications/85185656119

U2 - 10.3390/systems12020048

DO - 10.3390/systems12020048

M3 - Article

SN - 2079-8954

VL - 12

JO - Systems

JF - Systems

IS - 2

M1 - 48

ER -

AI Lifecycle Zero-Touch Orchestration within the Edge-to-Cloud Continuum for Industry 5.0

Abstract

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

knowlEdge: Towards AI powered manufacturing services, processes, and products in an edge-to-cloud-knowlEdge continuum for humans [in-the-loop]

Cite this

AI Lifecycle Zero-Touch Orchestration within the Edge-to-Cloud Continuum for Industry 5.0

Abstract

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Projects

knowlEdge: Towards AI powered manufacturing services, processes, and products in an edge-to-cloud-knowlEdge continuum for humans [in-the-loop]

Cite this