paper-with-me

홈 › Papers

Mapping back and forth between model predictive control and neural networks

2024-04-18 · Ross Drummond, Pablo R Baldivieso-Monasterios, Giorgio Valmorbida

Model predictive control (MPC) for linear systems with quadratic costs and linear constraints is shown to admit an exact representation as an implicit neural network. A method to "unravel" the implicit neural network of MPC into an explicit one is also introduced. As well as building links between model-based and data-driven control, these results emphasize the capability of implicit neural networks for representing solutions of optimisation problems, as such problems are themselves implicitly defined functions.

📄 PDF Abstract BibTeX arXiv:2404.12030

Code (0)

등록된 구현이 없습니다.

Tasks

Model Predictive Control

Similar Papers 제목 키워드 기반

The self-referring DNA and protein: a remark on physical and geometrical aspects

2018-04-10 · Tsvi Tlusty

All known life forms are based upon a hierarchy of interwoven feedback loops, operating over a cascade of space, time and energy scales. Among the most basic loops are those connecting DNA and proteins. For example, in g…

Predictive Modeling through Hyper-Bayesian Optimization

2023-08-01 · Manisha Senadeera, Santu Rana, Sunil Gupta, Svetha Venkatesh

Model selection is an integral problem of model based optimization techniques such as Bayesian optimization (BO). Current approaches often treat model selection as an estimation problem, to be periodically updated with o…

Bayesian OptimizationModel Selection

Data-driven Self-triggered Control via Trajectory Prediction

2022-07-18 · Wenjie Liu, Jian Sun, Gang Wang, Francesco Bullo 외

Self-triggered control, a well-documented technique for reducing the communication overhead while ensuring desired system performance, is gaining increasing popularity. However, existing methods for self-triggered contro…

Model Predictive ControlPredictionTrajectory Prediction

Learning Koopman Operators with Control Using Bi-level Optimization

2023-07-12 · Daning Huang, Muhammad Bayu Prasetyo, Yin Yu, Junyi Geng

The accurate modeling and control of nonlinear dynamical effects are crucial for numerous robotic systems. The Koopman formalism emerges as a valuable tool for linear control design in nonlinear systems within unknown en…

Nonlinear proper orthogonal decomposition for convection-dominated flows

2021-10-15 · Shady E. Ahmed, Omer San, Adil Rasheed, Traian Iliescu

Autoencoder techniques find increasingly common use in reduced order modeling as a means to create a latent space. This reduced order representation offers a modular data-driven modeling approach for nonlinear dynamical …

Time SeriesTime Series Analysis