no code implementations • 2 Nov 2023 • Eric Goubault, Roman Kniazev, Jeremy Ledent, Sergio Rajsbaum
By removing the assumption that models must be pure, we can go beyond the usual Kripke semantics and study epistemic logics where the number of agents participating in a world can vary.
no code implementations • 14 Sep 2023 • Eric Goubault, Sylvie Putot
We propose an approach to compute inner and outer-approximations of the sets of values satisfying constraints expressed as arbitrarily quantified formulas.
1 code implementation • 14 Jan 2022 • Franck Djeumou, Cyrus Neary, Eric Goubault, Sylvie Putot, Ufuk Topcu
Neural ordinary differential equations (NODEs) -- parametrizations of differential equations using neural networks -- have shown tremendous promise in learning models of unknown continuous-time dynamical systems from data.
1 code implementation • 14 Sep 2021 • Franck Djeumou, Cyrus Neary, Eric Goubault, Sylvie Putot, Ufuk Topcu
The physics-informed constraints are enforced via the augmented Lagrangian method during the model's training.
no code implementations • 30 Jul 2021 • Eric Goubault, Sébastien Palumby, Sylvie Putot, Louis Rustenholz, Sriram Sankaranarayanan
This paper studies the problem of range analysis for feedforward neural networks, which is a basic primitive for applications such as robustness of neural networks, compliance to specifications and reachability analysis of neural-network feedback systems.
no code implementations • 30 Jul 2021 • Maria Luiza Costa Vianna, Eric Goubault, Sylvie Putot
We study learning based controllers as a replacement for model predictive controllers (MPC) for the control of autonomous vehicles.
no code implementations • 27 Jul 2021 • Nicola Bernini, Mikhail Bessa, Rémi Delmas, Arthur Gold, Eric Goubault, Romain Pennec, Sylvie Putot, François Sillion
We explore the reinforcement learning approach to designing controllers by extensively discussing the case of a quadcopter attitude controller.
1 code implementation • 27 Jan 2021 • Eric Goubault, Sylvie Putot
We consider the problem of under and over-approximating the image of general vector-valued functions over bounded sets, and apply the proposed solution to the estimation of reachable sets of uncertain non-linear discrete-time dynamical systems.
no code implementations • NeurIPS 2020 • Sriram Sankaranarayanan, Yi Chou, Eric Goubault, Sylvie Putot
In this paper, we propose polynomial forms to represent distributions of state variables over time for discrete-time stochastic dynamical systems.
no code implementations • 11 Nov 2020 • Franck Djeumou, Abraham P. Vinod, Eric Goubault, Sylvie Putot, Ufuk Topcu
Besides, $\texttt{DaTaControl}$ achieves near-optimal control and is suitable for real-time control of such systems.
no code implementations • 27 Sep 2020 • Franck Djeumou, Abraham P. Vinod, Eric Goubault, Sylvie Putot, Ufuk Topcu
We investigate the problem of data-driven, on-the-fly control of systems with unknown nonlinear dynamics where data from only a single finite-horizon trajectory and possibly side information on the dynamics are available.