An end-to-end data-driven optimisation framework for constrained trajectories
This work addresses the problem of optimizing constrained trajectories without requiring exact knowledge of system dynamics, which is beneficial for engineers and planners in fields like aeronautics and sailing where dynamics are complex or unknown.
This paper introduces a data-driven, dynamics-free framework for optimizing constrained trajectories by decomposing them onto a function basis and using a maximum a posteriori approach. It was applied to aeronautics and sailing route optimization, achieving "commanding results."
Many real-world problems require to optimise trajectories under constraints. Classical approaches are based on optimal control methods but require an exact knowledge of the underlying dynamics, which could be challenging or even out of reach. In this paper, we leverage data-driven approaches to design a new end-to-end framework which is dynamics-free for optimised and realistic trajectories. We first decompose the trajectories on function basis, trading the initial infinite dimension problem on a multivariate functional space for a parameter optimisation problem. A maximum \emph{a posteriori} approach which incorporates information from data is used to obtain a new optimisation problem which is regularised. The penalised term focuses the search on a region centered on data and includes estimated linear constraints in the problem. We apply our data-driven approach to two settings in aeronautics and sailing routes optimisation, yielding commanding results. The developed approach has been implemented in the Python library PyRotor.