Descripción del proyecto
Inteligencia artificial fiable para las industrias
Cada vez más organizaciones y empresas incorporan tecnologías de inteligencia artificial (IA) para la producción y otros fines. Por desgracia, a pesar de los múltiples beneficios potenciales de la IA, su adopción a gran escala ha estado plagada de dificultades debido a la falta de validez, ética y explicabilidad. El equipo del proyecto ULTIMATE, financiado con fondos europeos, desarrollará un modelo de IA híbrida de nivel industrial que abordará estos retos y permitirá que esta tecnología se extienda aún más por el sector industrial. Para lograrlo, en la iniciativa se proporcionará a las partes interesadas métodos y herramientas que garanticen la fiabilidad (a efectos de aceptación) a lo largo de todo el ciclo de vida del modelo de IA híbrida, con el fin de mejorar la cooperación entre los trabajadores y la IA.
Objetivo
AI has entered the business mainstream, opening opportunities to boost productivity and innovation but suffer limitations hindering wider adoption of model-based or data-driven AI algorithms in industrial settings. Both approaches complement each other and form a critical foundation for the adoption of AI in industry. However, hybrid AI does not fully address the issue of trust (validity, explainability, and ethics). ULTIMATE will pioneer the development of industrial-grade hybrid AI based on three stages to ensure trustworthiness, relying on interdisciplinary data sources and adhering to physical constraints (1st stage), as well as the development of tools for explaining, evaluating and validating hybrid AI algorithms and asserting their adherence to ethical and legal regulations (2nd stage). These will be exemplified using real-world industrial use cases (3rd stage) in the Robotics (collaboration between human and robots for logistics activities) and Space domains (Failure detection for satellites) to promote the widespread adoption of hybrid AI in industry.
The breakthrough generic hybrid AI architectures with improved explainability and interpretability and the predictive model on trustworthiness developed in ULTIMATE will provide industrials with improved shopfloor efficiency (reduction of downtime by 30% and of operational costs) and empower their staff through trustful human/machine cooperation allowing highly skilled jobs and increasing decision power and safety. This will be beneficial to European industry to gain pre-emptive advantage in the market of industrial AI solutions and will eventually increase trustworthiness in the use of hybrid AI components by the wider public.
Extending over 36 months, the ULTIMATE project brings together key industrial stakeholders, with relevant end-users from manufacturing sectors, leading academic and research institutions, and SMEs to collaboratively investigate and lead the development of hybrid AI approaches.
Ámbito científico
- natural sciencescomputer and information sciencesartificial intelligence
- engineering and technologycivil engineeringstructural engineeringstructural health monitoring
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringroboticsautonomous robots
- social scienceseconomics and businesseconomicsproduction economicsproductivity
Palabras clave
Programa(s)
Régimen de financiación
HORIZON-RIA - HORIZON Research and Innovation ActionsCoordinador
92190 MEUDON
Francia