On the 17th of October, in Toulouse, Optit participated to the first meeting between the members of the TUPLES (Trustworthy Planning and scheduling with Learning and ExplanationS) consortium. TUPLES is an ambitious and challenging project funded by the European Union in the Horizon Europe framework program. It’s aims is to develop new guidelines and practices to make P&S (Programme & Scheduling) and AI systems more reliable, secure, and above all understandable to facilitate their adoption in everyday life.
Task planning and scheduling has always been at the heart of AI and of problems related to robotics, defense, space exploration, manufacturing and logistics. Unfortunately, current methods, whether model-based or data-driven AI, do not inspire enough confidence to be massively adopted and have the expected impact: the former due to a lack of efficiency and adaptability to non-modelled situations, and the latter due to a lack of transparency, robustness, and safety guarantees.
TUPLES (TrUstworthy Planning and scheduling with Learning and ExplanationS) is a 3 year project aiming to obtain scalable, yet transparent, robust and safe algorithmic solutions for P&S. It will contribute to a more integrated and human-centered approach to the development of P&S tools, in order to increase confidence in these systems and accelerate their adoption.
The cornerstones of TUPLES’ scientific contributions will be:
– 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;
– 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.
TUPLES will demonstrate and evaluate these 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.
The project will have a three-year duration. Optit contributes to the TUPLES project by providing 2 use cases, one in energy and one in waste management, based on more than 10 years of experience in each field. Academic partners, building on current approaches and methodologies implemented by Optit, will explore new means to improve performance and ability to comply with Trustworthy AI guidelines (with a focus on robustness and provability).
In addition, Optit is leading the Work Package that will manage dissemination and communication for the entire consortium, as well as the development of the Trusted AI self-assessment tool and guidelines.
Links to Press Release