Descripción del proyecto
Crear una inteligencia artificial fiable para la planificación y la ordenación
Los actuales métodos de inteligencia artificial destinados a la planificación y la ordenación (PyO), tanto si se basan en modelos como en datos, no inspiran la suficiente confianza para que se adopten de forma masiva y logren su posible repercusión. El proyecto TUPLES, financiado con fondos europeos, contribuirá a una metodología integrada y centrada en las personas a fin de desarrollar herramientas de PyO con el objetivo de aumentar la confianza y su adopción. En general, tiene tres objetivos. En primer lugar, desarrollar métodos híbridos PyO que combinen la eficacia, flexibilidad y adaptabilidad de las metodologías de aprendizaje basadas en datos con la solidez, fiabilidad y claridad de los métodos de razonamiento basados en modelos. En segundo lugar, diseñar métodos para verificar y explicar las soluciones producidas por los sistemas de PyO. Y, por último, realizar estudios de casos, desde la asistencia a pilotos de aviones hasta la gestión de equipos de fútbol y la recogida de residuos.
Objetivo
Planning and scheduling (P&S) is a core area of AI. Its aim is to build systems that assist humans in planning, organising and optimising courses of action to achieve complex objectives. Despite the pressing need for decision-support systems for P&S applications in industry and public services, current approaches do not satisfy essential properties of trustworthy AI, such as transparency, explainability, robustness, safety and scalability.
TUPLES is a 3 year project aiming to obtain scalable, yet transparent, robust and safe algorithmic solutions for P&S. The cornerstones of our scientific contributions will be (1) combining symbolic P&S methods with data-driven methods to benefit from the scalability and modelling power of the latter, while gaining the transparency, robustness, and safety of the former and (2) developing rigorous explanations and verification approaches for ensuring the transparency, robustness, and safety of a sequence of interacting machine learned decisions. Both of these challenges are at the forefront of AI research.
We will demonstrate and evaluate our novel and rigorous methods in a laboratory environment, on a range of use-cases in manufacturing, aircraft operations, sport management, waste collection, and energy management. Our results also include practical guidelines derived from the lessons learnt in this process, and open-source software tools and test environments enabling the human-centered development and assessment of trustworthy P&S systems. Expected outcomes include increased productivity, decreased environmental footprint and the empowerment of workers in the above sectors. These could translate into huge economic, environmental and social impacts if trustworthiness ends up driving mass adoption of P&S.
The TUPLES consortium includes world-leading researchers in several fields of AI (P&S, constraints, machine learning, explanations), humanities and social sciences (psychology, law, ethics), and experts of their applications.
Ámbito científico
- social sciencessociologygovernancepublic services
- engineering and technologyenvironmental engineeringwaste management
- social scienceseconomics and businesseconomicsproduction economicsproductivity
- social sciencespsychology
- natural sciencescomputer and information sciencesartificial intelligencemachine learning
Palabras clave
Programa(s)
Régimen de financiación
HORIZON-RIA - HORIZON Research and Innovation ActionsCoordinador
31000 Toulouse
Francia