Search Results for author: Franck Djeumou

Found 12 papers, 3 papers with code

How to Learn and Generalize From Three Minutes of Data: Physics-Constrained and Uncertainty-Aware Neural Stochastic Differential Equations

no code implementations10 Jun 2023 Franck Djeumou, Cyrus Neary, Ufuk Topcu

We present a framework and algorithms to learn controlled dynamics models using neural stochastic differential equations (SDEs) -- SDEs whose drift and diffusion terms are both parametrized by neural networks.

Inductive Bias Model-based Reinforcement Learning +1

Physics-Informed Kernel Embeddings: Integrating Prior System Knowledge with Data-Driven Control

no code implementations9 Jan 2023 Adam J. Thorpe, Cyrus Neary, Franck Djeumou, Meeko M. K. Oishi, Ufuk Topcu

Our proposed approach incorporates prior knowledge of the system dynamics as a bias term in the kernel learning problem.

Task-Guided IRL in POMDPs that Scales

1 code implementation30 Dec 2022 Franck Djeumou, Christian Ellis, Murat Cubuktepe, Craig Lennon, Ufuk Topcu

First, they require an excessive amount of data due to the information asymmetry between the expert and the learner.

Unity

Taylor-Lagrange Neural Ordinary Differential Equations: Toward Fast Training and Evaluation of Neural ODEs

1 code implementation14 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.

Density Estimation Image Classification +1

Neural Networks with Physics-Informed Architectures and Constraints for Dynamical Systems Modeling

1 code implementation14 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.

Inductive Bias

Probabilistic Control of Heterogeneous Swarms Subject to Graph Temporal Logic Specifications: A Decentralized and Scalable Approach

no code implementations29 Jun 2021 Franck Djeumou, Zhe Xu, Murat Cubuktepe, Ufuk Topcu

Specifically, we study a setting in which the agents move along the nodes of a graph, and the high-level task specifications for the swarm are expressed in a recently-proposed language called graph temporal logic (GTL).

Learning to Reach, Swim, Walk and Fly in One Trial: Data-Driven Control with Scarce Data and Side Information

no code implementations19 Jun 2021 Franck Djeumou, Ufuk Topcu

We develop a learning-based control algorithm for unknown dynamical systems under very severe data limitations.

Model Predictive Control

Task-Guided Inverse Reinforcement Learning Under Partial Information

no code implementations28 May 2021 Franck Djeumou, Murat Cubuktepe, Craig Lennon, Ufuk Topcu

Nevertheless, the resulting formulation is still nonconvex due to the intrinsic nonconvexity of the so-called forward problem, i. e., computing an optimal policy given a reward function, in POMDPs.

reinforcement-learning Reinforcement Learning (RL)

Safety-Constrained Learning and Control using Scarce Data and Reciprocal Barriers

no code implementations13 May 2021 Christos K. Verginis, Franck Djeumou, Ufuk Topcu

We develop a control algorithm that ensures the safety, in terms of confinement in a set, of a system with unknown, 2nd-order nonlinear dynamics.

On-The-Fly Control of Unknown Systems: From Side Information to Performance Guarantees through Reachability

no code implementations11 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.

On-The-Fly Control of Unknown Smooth Systems from Limited Data

no code implementations27 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.