CE10 - Industrie et usine du futur: Homme, organisation, technologies

AI for Cognitive Cyber-Physical Systems interoperability – AI4C2PS

Submission summary

The next generation of Cyber-Physical Enterprises must reach a satisfactory level of flexibility and efficiency that better integrates humans and give human-machine teams complete autonomy for some tasks including ad-hoc reconfigurations and non-predefined problem-solving. Efficient Human-CPS collaboration can happen only when Interoperability also includes the cognitive level to promote understanding and learning of the other’s behaviour and to adapt and react accordingly. The resulting Human-CPS interaction should optimize the quality of both the production process and the user experience. AI4C2PS seeks then at bringing Human-CPS Cognitive Interoperability to the Cyber-Physical Enterprise. It will answer to this main research question: How Human-CPS collaboration can be supported by Digital Twins embedding Neuro-Symbolic AI, to improve CPE decision-making power and human integration in evolving and changing context? Exploiting the Digital Twin (DT) concept in a decentralised way where each CPS and Human is twinned, AI4C2PS seeks to bridge Human Modelling, Knowledge Representation and Reasoning, and Deep Reinforcement Learning to build cognitive interoperability within the resulting system-of-systems.

Project coordination

Hervé PANETTO (Centre de recherche en automatique de Nancy)

The author of this summary is the project coordinator, who is responsible for the content of this summary. The ANR declines any responsibility as for its contents.

Partner

ORISUN
CRAN Centre de recherche en automatique de Nancy
LIST Luxembourg Institute of Science and Technology

Help of the ANR 479,999 euros
Beginning and duration of the scientific project: February 2023 - 42 Months

Useful links

Explorez notre base de projets financés

 

 

ANR makes available its datasets on funded projects, click here to find more.

Sign up for the latest news:
Subscribe to our newsletter