TUPLES

The cornerstones of our scientific contributions in Trustworthy AI 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.

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.

EXPECTED IMPACT

OUTCOME 1

To develop hybrid planning and scheduling methods that combine the efficiency, flexibility, and adaptability of data-driven learning approaches with the robustness, reliability, and clarity of model-based reasoning methods. This will require the ability  to integrate learned models into the core of current planning and scheduling approaches that rely on constraint satisfaction, combinatorial optimization, and heuristic search algorithms.

OUTCOME 2

To develop verification and explanation methods capable of reasoning about the properties of the solutions produced by planning and scheduling systems, in particular when these are represented by neural networks.