paper-with-me

Papers

Reliably-stabilizing piecewise-affine neural network controllers

2021-11-13 · Filippo Fabiani, Paul J. Goulart

A common problem affecting neural network (NN) approximations of model predictive control (MPC) policies is the lack of analytical tools to assess the stability of the closed-loop system under the action of the NN-based controller. We present a general procedure to quantify the performance of such a controller, or to design minimum complexity NNs with rectified linear units (ReLUs) that preserve the desirable properties of a given MPC scheme. By quantifying the approximation error between NN-based and MPC-based state-to-input mappings, we first establish suitable conditions involving two key quantities, the worst-case error and the Lipschitz constant, guaranteeing the stability of the closed-loop system. We then develop an offline, mixed-integer optimization-based method to compute those quantities exactly. Together these techniques provide conditions sufficient to certify the stability and performance of a ReLU-based approximation of an MPC control law.

📄 PDF Abstract BibTeX arXiv:2111.07183

Code (0)

등록된 구현이 없습니다.

Tasks

Model Predictive Control

Similar Papers 제목 키워드 기반

Reachability analysis for piecewise affine systems with neural network-based controllers

2024-11-06 · Dieter Teichrib, Moritz Schulze Darup

Neural networks (NN) have been successfully applied to approximate various types of complex control laws, resulting in low-complexity NN-based controllers that are fast to evaluate. However, when approximating control la…

Systematic Stabilization of Constrained Piecewise Affine Systems

2022-02-28 · Reza Lavaei, Leila Bridgeman

This paper presents an efficient, offline method to simultaneously synthesize controllers and seek closed-loop Lyapunov functions for constrained piecewise affine systems on triangulated subsets of the admissible states.…

An integral sliding-mode parallel control approach for general nonlinear systems via piecewise affine linear models

2021-01-13 · ChunYang Zhang, Qing Gao, Yue Deng, Jianbin Qiu

The fundamental problem of stabilizing a general nonaffine continuous-time nonlinear system is investigated via piecewise affine linear models (PALMs) in this article. A novel integral sliding-mode parallel control (ISMP…

A mixed-integer framework for analyzing neural network-based controllers for piecewise affine systems with bounded disturbances

2025-04-15 · Dieter Teichrib, Moritz Schulze Darup

We present a method for representing the closed-loop dynamics of piecewise affine (PWA) systems with bounded additive disturbances and neural network-based controllers as mixed-integer (MI) linear constraints. We show th…

Systematic, Lyapunov-Based, Safe and Stabilizing Controller Synthesis for Constrained Nonlinear Systems

2022-03-05 · Reza Lavaei, Leila Bridgeman

A controller synthesis method for state- and input-constrained nonlinear systems is presented that seeks continuous piecewise affine (CPA) Lyapunov-like functions and controllers simultaneously. Non-convex optimization p…