Approximate Closed-Loop Robust Model Predictive Control With Guaranteed Stability and Constraint Satisfaction

The real-time implementation of closed-loop robust model predictive control (MPC) schemes is an important challenge for fast systems, as their solution complexity depends strongly on the system size, control policy parametrization, and prediction horizon. We look to address this problem by approximating the implicitly-defined MPC controller using deep learning. Although the resulting neural network approximation has a small memory footprint and can be efficiently computed, it does not guarantee robust constraint satisfaction or stability. We propose a novel projection-based strategy that is capable of providing a certificate of robust feasibility and input-to-state stability in real-time. We also show how this projection operator can be formulated as a parametric quadratic program that is solvable offline. The advantages of the proposed approach are demonstrated on a benchmark case study.

[1]  Manfred Morari,et al.  Large Scale Model Predictive Control with Neural Networks and Primal Active Sets , 2019, ArXiv.

[2]  Mazen Alamir,et al.  Computing control invariant sets in high dimension is easy , 2018, ArXiv.

[3]  Bart De Moor,et al.  On efficient computation of low-complexity controlled invariant sets for uncertain linear systems , 2010, Int. J. Control.

[4]  Efstratios N. Pistikopoulos,et al.  Explicit Robust Model Predictive Control , 2009 .

[5]  Mark Cannon,et al.  On the Computation of $\lambda$- Contractive Sets for Linear Constrained Systems , 2016, IEEE Transactions on Automatic Control.

[6]  Lorenz T. Biegler,et al.  On the implementation of an interior-point filter line-search algorithm for large-scale nonlinear programming , 2006, Math. Program..

[7]  Mircea Lazar,et al.  Minkowski terminal cost functions for MPC , 2012, Autom..

[8]  Sebastian Engell,et al.  Multi-stage nonlinear model predictive control applied to a semi-batch polymerization reactor under uncertainty , 2013 .

[9]  Alberto Bemporad,et al.  Complexity and convergence certification of a block principal pivoting method for box-constrained quadratic programs , 2019, Autom..

[10]  Alberto Bemporad,et al.  The explicit linear quadratic regulator for constrained systems , 2003, Autom..

[11]  Franco Blanchini,et al.  Set-theoretic methods in control , 2007 .

[12]  H. J. Ferreau,et al.  An online active set strategy to overcome the limitations of explicit MPC , 2008 .

[13]  Alberto Bemporad,et al.  Robust explicit MPC based on approximate multiparametric convex programming , 2004, IEEE Transactions on Automatic Control.

[14]  Alberto Bemporad,et al.  Exact Complexity Certification of Active-Set Methods for Quadratic Programming , 2017, IEEE Transactions on Automatic Control.

[15]  A. Mesbah,et al.  Stochastic Model Predictive Control: An Overview and Perspectives for Future Research , 2016, IEEE Control Systems.

[16]  Manfred Morari,et al.  Computational Complexity Certification for Real-Time MPC With Input Constraints Based on the Fast Gradient Method , 2012, IEEE Transactions on Automatic Control.

[17]  Tor Arne Johansen,et al.  Toward Dependable Embedded Model Predictive Control , 2017, IEEE Systems Journal.

[18]  Alexander Domahidi,et al.  Circuit generation for efficient projection onto polyhedral sets in first-order methods , 2015, 2015 European Control Conference (ECC).

[19]  Benjamin Karg,et al.  Efficient Representation and Approximation of Model Predictive Control Laws via Deep Learning , 2018, IEEE Transactions on Cybernetics.

[20]  Andrew R. Barron,et al.  Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.

[21]  Vijay Kumar,et al.  Approximating Explicit Model Predictive Control Using Constrained Neural Networks , 2018, 2018 Annual American Control Conference (ACC).

[22]  Manfred Morari,et al.  Multi-Parametric Toolbox 3.0 , 2013, 2013 European Control Conference (ECC).

[23]  Stephen P. Boyd,et al.  Fast Model Predictive Control Using Online Optimization , 2010, IEEE Transactions on Control Systems Technology.

[24]  Alberto Bemporad,et al.  Robust model predictive control: A survey , 1998, Robustness in Identification and Control.

[25]  Béla Lantos,et al.  Explicit MPC-Based RBF Neural Network Controller Design With Discrete-Time Actual Kalman Filter for Semiactive Suspension , 2015, IEEE Transactions on Control Systems Technology.

[26]  E. Kerrigan.  Robust Constraint Satisfaction: Invariant Sets and Predictive Control , 2000 .

[27]  David Q. Mayne,et al.  Model predictive control: Recent developments and future promise , 2014, Autom..

[28]  Vu C. Dinh,et al.  Support Vector Machine Informed Explicit Nonlinear Model Predictive Control Using Low-Discrepancy Sequences , 2017, IEEE Transactions on Automatic Control.

[29]  Riccardo Scattolini,et al.  Regional Input-to-State Stability for Nonlinear Model Predictive Control , 2006, IEEE Transactions on Automatic Control.