AutoKoopman - automated Koopman operator methods for data-driven dynamical systems analysis and control.

Model-based Control using Koopman Operators

Koopman operator

In this work, we present a novel approach that combines the power of Koopman operators and deep neural networks to generate a linear representation of the Duffing oscillator. This approach enables effective parameter estimation and accurate prediction of the oscillator's future behavior.

This repository contains the code for bilinear models for serial manipulators and the corresponding ZNN controller described in paper titled "Real-Time Constrained Tracking Control of Redundant Manipulators Using a Koopman-Zeroing Neural Network Framework".

A repo for using different dynamic world modeling for planning, prediction and control: including State-Space Models (SSMs) and Video Models

a little library to help me with things involving Koopman operators

project for my essay on how to use neural networks to linearise nonlinear dynamical systems

Library for the analysis of time-evolving graphs

Code for running the analyses from the article "Propofol destabilizies neural dynamics across cortex"

A repository for an Generalized Momenta based Koopman algorithm described for the paper titled "Generalized Momenta-Based Koopman Formalism for Robust Control of Euler-Lagrangian Systems".

koopman operator examples

For research into the application of Koopman operators at Boston University.

Transfer operator toolbox for numpy/torch.

Terrain-specific Koopman operators for prediction and MPC of off-road vehicles on deformable terrain.

This repository is a supplementary documentation for the Multi-Model Parameterized Koopman (MMPK) framework capturing results through software and hardware deployments

🏎️ Model and simulate vehicle suspension dynamics using Python and Laplace Transforms for accurate analysis of second-order LTI systems.