Mapping back and forth between model predictive control and neural networks
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Model Predictive ControlSimilar Papers 제목 키워드 기반
The self-referring DNA and protein: a remark on physical and geometrical aspects
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
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 SelectionData-driven Self-triggered Control via Trajectory Prediction
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 PredictionLearning Koopman Operators with Control Using Bi-level Optimization
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
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