AReN: Assured ReLU NN Architecture for Model Predictive Control of LTI Systems

11/05/2019
by   James Ferlez, et al.
0

In this paper, we consider the problem of automatically designing a Rectified Linear Unit (ReLU) Neural Network (NN) architecture that is sufficient to implement the optimal Model Predictive Control (MPC) strategy for an LTI system with quadratic cost. Specifically, we propose AReN, an algorithm to generate Assured ReLU Architectures. AReN takes as input an LTI system with quadratic cost specification, and outputs a ReLU NN architecture with the assurance that there exist network weights that exactly implement the associated MPC controller. AReN thus offers new insight into the design of ReLU NN architectures for the control of LTI systems: instead of training a heuristically chosen NN architecture on data – or iterating over many architectures until a suitable one is found – AReN can suggest an adequate NN architecture before training begins. While several previous works were inspired by the fact that both ReLU NN controllers and optimal MPC controller are both Continuous, Piecewise-Linear (CPWL) functions, exploiting this similarity to design NN architectures with correctness guarantees has remained elusive. AReN achieves this using two novel features. First, we reinterpret a recent result about the implementation of CPWL functions via ReLU NNs to show that a CPWL function may be implemented by a ReLU architecture that is determined by the number of distinct affine regions in the function. Second, we show that we can efficiently over-approximate the number of affine regions in the optimal MPC controller without solving the MPC problem exactly. Together, these results connect the MPC problem to a ReLU NN implementation without explicitly solving the MPC and directly translates this feature to a ReLU NN architecture that comes with the assurance that it can implement the MPC controller. We show through numerical results the effectiveness of AReN in designing an NN architecture.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/20/2020

Two-Level Lattice Neural Network Architectures for Control of Nonlinear Systems

In this paper, we consider the problem of automatically designing a Rect...
research
06/09/2020

In Proximity of ReLU DNN, PWA Function, and Explicit MPC

Rectifier (ReLU) deep neural networks (DNN) and their connection with pi...
research
09/21/2021

Assured Neural Network Architectures for Control and Identification of Nonlinear Systems

In this paper, we consider the problem of automatically designing a Rect...
research
06/14/2022

Tailored max-out networks for learning convex PWQ functions

Convex piecewise quadratic (PWQ) functions frequently appear in control ...
research
03/18/2023

Hybrid Systems Neural Control with Region-of-Attraction Planner

Hybrid systems are prevalent in robotics. However, ensuring the stabilit...
research
12/07/2021

Tailored neural networks for learning optimal value functions in MPC

Learning-based predictive control is a promising alternative to optimiza...
research
06/02/2022

Data-Driven Linear Koopman Embedding for Model-Predictive Power System Control

This paper presents a linear Koopman embedding for model predictive emer...

Please sign up or login with your details

Forgot password? Click here to reset