Skip to main content
CORDIS - Forschungsergebnisse der EU
CORDIS

Flexibilization of complex Ecosystems using Democratic AI based Decision Support and Recommendation Systems at Work

Projektbeschreibung

Mit hybrider Entscheidungsfindung den Produktionsprozess optimieren

Ein hybrides Entscheidungsfindungsmodell nutzt sowohl an Maschinen als auch am Menschen orientierte zentrierte Elemente. Es kann jedoch zu einer echten Herausforderung werden, Menschen und Maschinen zusammenzubringen. Das EU-finanzierte Projekt FAIRWork wird ein System zur Entscheidungsunterstützung entwickeln, das digitale Zwillinge integriert, den gesamten Produktionsprozess entsprechend mehrerer Parameter optimiert und die Entscheidungsfindung demokratisiert, sodass Arbeitskräfte und Maschinen an der Entscheidungsfindung teilhaben können. Das Projekt kombiniert modellbasierte Ansätze zur transparenten Gestaltung, Simulation und Verbesserung der Entscheidungsfindung, Labormodelle für Co-Creation und physikalische Experimente als Kommunikationsmedien sowie zuverlässige Angaben zu Daten und KI-Algorithmen.

Ziel

We provide a decision support system that (a) integrates digital twins to optimize the overall production process according multiple parameters, and (b) democratizes decision making granting human worker and machines a say during decision making. Each individual demand is consolidated to achieve a decision support, which is then optimized.
We combine (a) model-based approaches to transparently design, simulate and improve decision making, (b) co-creation laboratory using models and physical experiments as communication media to all actors and, (c) reliability indication of data and AI algorithms.
Those models can be assessed according legal, ethical, security and safety concerns and in case of approval ensure that only compliant models are used for decision making.
Hybrid decision making is provided by combining human- and machine-centric knowledge representation into a holistic model. Simulations on time, cost, quality, safety or energy efficiency contribute to transparent decision making, which evolves via model changes.
BOC provides graphical modelling enabling intuitive knowledge representations for humans. JOTNE provides data repositories for machines. JR provides data marketplaces and optimizations. MORE enable decentralized decision making with AI. RWTH provides both (a) AI and intuitive machine interaction and (b) social and ethical guidance for trustful decision making.
The use cases of the car manufacturer CRF and the robot plant provider FLEX are challenged by human and machine interaction, complex environment interactions and influence factors requiring continuous re-arrangements. The challenge is to consider each actors needs in a concise and complex situation still targeting an overall optimization.
The non-profit organization OMiLAB provides its world-wide network on modelling omilab.org and interacts with DIH, PPP on AI, Data and Robotics and contribute with corresponding CSA as part of their mission.

Koordinator

BOC PRODUCTS & SERVICES AG
Netto-EU-Beitrag
€ 549 806,00
Adresse
OPERNGASSE 20B
1040 Wien
Österreich

Auf der Karte ansehen

Region
Ostösterreich Wien Wien
Aktivitätstyp
Private for-profit entities (excluding Higher or Secondary Education Establishments)
Links
Gesamtkosten
€ 785 437,50

Beteiligte (8)