International Journal of Robust and Nonlinear Control

Volume 31, Issue 18 pp. 8813-8829

SPECIAL ISSUE ARTICLE

Online learning constrained model predictive control based on double prediction

J. M. Manzano,

Corresponding Author

J. M. Manzano

[email protected]

orcid.org/0000-0003-2932-5581

Departamento de Ingniería de Sistemas y Automática, Universidad de Sevilla, Sevilla, Spain

Correspondence J. M. Manzano, Departamento de Ingniería de Sistemas y Automática, Universidad de Sevilla, Camino de los Descubrimientos s/n 41092, Sevilla, Spain.

Email: [email protected]

Search for more papers by this author

D. Muñoz de la Peña,

D. Muñoz de la Peña

Departamento de Ingniería de Sistemas y Automática, Universidad de Sevilla, Sevilla, Spain

Search for more papers by this author

J. Calliess,

J. Calliess

Oxford-Man Institute of Quantitative Finance, University of Oxford, Oxford, UK

Search for more papers by this author

D. Limon,

D. Limon

orcid.org/0000-0001-9334-7289

Departamento de Ingniería de Sistemas y Automática, Universidad de Sevilla, Sevilla, Spain

Search for more papers by this author

J. M. Manzano,

Corresponding Author

J. M. Manzano

[email protected]

orcid.org/0000-0003-2932-5581

Departamento de Ingniería de Sistemas y Automática, Universidad de Sevilla, Sevilla, Spain

Correspondence J. M. Manzano, Departamento de Ingniería de Sistemas y Automática, Universidad de Sevilla, Camino de los Descubrimientos s/n 41092, Sevilla, Spain.

Email: [email protected]

Search for more papers by this author

D. Muñoz de la Peña,

D. Muñoz de la Peña

Departamento de Ingniería de Sistemas y Automática, Universidad de Sevilla, Sevilla, Spain

Search for more papers by this author

J. Calliess,

J. Calliess

Oxford-Man Institute of Quantitative Finance, University of Oxford, Oxford, UK

Search for more papers by this author

D. Limon,

D. Limon

orcid.org/0000-0001-9334-7289

Departamento de Ingniería de Sistemas y Automática, Universidad de Sevilla, Sevilla, Spain

Search for more papers by this author

First published: 07 September 2020

https://doi.org/10.1002/rnc.5124

Citations: 3

[Correction added on 22 September 2020, after first online publication: ‘model predictive controller’ has been changed to ‘model predictive control’ in the article title.]

Funding information: Ministerio de Economía y Competitividad, DPI2016-76493-C3-1-R; Universidad de Sevilla, VI-PPITUS

Share a link

Email
Wechat
Bluesky

Summary

A data-based predictive controller is proposed, offering both robust stability guarantees and online learning capabilities. To merge these two properties in a single controller, a double-prediction approach is taken. On the one hand, a safe prediction is computed using Lipschitz interpolation on the basis of an offline identification dataset, which guarantees safety of the controlled system. On the other hand, the controller also benefits from the use of a second online learning-based prediction as measurements incrementally become available over time. Sufficient conditions for robust stability and constraint satisfaction are given. Illustrations of the approach are provided in a simulated case study.

REFERENCES

1Fisac JF, Akametalu AK, Zeilinger MN, Kaynama S, Gillula J, Tomlin CJ. A general safety framework for learning-based control in uncertain robotic systems. IEEE Trans Automat Control. 2018; 64(7): 2737-2752.
10.1109/TAC.2018.2876389
Web of Science® Google Scholar
2Piga D, Formentin S, Bemporad A. Direct data-driven control of constrained systems. IEEE Trans Control Syst Technol. 2017; 26(4): 1422-1429.
10.1109/TCST.2017.2702118
Web of Science® Google Scholar
3Salvador JR, Ramirez DR, Alamo T, Muñoz de la Peña D. Offset free data driven control: application to a process control trainer. IET Control Theory Appl. 2019; 13(18): 3096-3106.
10.1049/iet-cta.2019.0376
Web of Science® Google Scholar
4 Salvador JR, Muñoz de la Peña D, Ramirez DR, Alamo T. Predictive control of a water distribution system based on process historian data. Opt Control Appl Methods. 2019; 41(2): 571-586.
10.1002/oca.2559
Web of Science® Google Scholar
5Maiworm M, Limon D, Manzano JM, Findeisen R. Stability of Gaussian process learning based output feedback model predictive control. IFAC-PapersOnLine. 2018; 51(20): 455-461.
10.1016/j.ifacol.2018.11.047
Google Scholar
6Smarra F, Jain A, Ambrosini D, D'Innocenzo A, Mangharam R. Data-driven model predictive control using random forests for building energy optimization and climate control. Appl Energy. 2018; 226: 1252-1272.
10.1016/j.apenergy.2018.02.126
Web of Science® Google Scholar
7 Hewing L, Wabersich KP, Menner M, Zeilinger MN. Learning-based model predictive control: toward safe learning in control. Ann Rev Control Robotics Autonom Syst. 2020; 3: 269-296.
10.1146/annurev-control-090419-075625
Google Scholar
8Sutton RS, Barto AG. Introduction to Reinforcement Learning. Cambridge, MA: MIT Press; 1998.
10.1109/TNN.1998.712192
Google Scholar
9Wittenmark B. Adaptive Dual Control Methods: An Overview. Amsterdam, Netherlands: Elsevier; 1995: 67-72.
Google Scholar
10Benosman M. Model-based vs data-driven adaptive control: an overview. Int J Adapt Control Signal Process. 2018; 32(5): 753-776.
10.1002/acs.2862
Google Scholar
11Beliakov G. Interpolation of Lipschitz functions. J Comput Appl Math. 2006; 196(1): 20-44.
10.1016/j.cam.2005.08.011
Web of Science® Google Scholar
12Sukharev AG. Optimal method of constructing best uniform approximations for functions of a certain class. USSR Comput Math Math Phys. 1978; 18(2): 21-31.
10.1016/0041-5553(78)90035-6
Google Scholar
13Calliess JP. Lazily adapted constant kinky inference for nonparametric regression and model-reference adaptive control; 2016. arXiv preprint arXiv:1701.00178.
Google Scholar
14 Milanese M, Novara C. Set membership identification of nonlinear systems. Automatica. 2004; 40(6): 957-975.
10.1016/j.automatica.2004.02.002
Web of Science® Google Scholar
15Calliess JP. Lipschitz optimisation for Lipschitz interpolation. Paper presented at: Proceedings of the American Control Conference (ACC); vol 2017, 2017:3141-3146; IEEE.
Google Scholar
16Canale M, Fagiano L, Signorile MC. Nonlinear model predictive control from data: a set membership approach. Int J Robust Nonlinear Control. 2014; 24(1): 123-139.
10.1002/rnc.2878
Web of Science® Google Scholar
17Calliess JP. Conservative Decision-Making and Inference in Uncertain Dynamical Systems [PhD thesis]. University of Oxford; 2014.
Google Scholar
18Manzano JM, Limon D, Muñoz de la Peña D, Calliess J-P. Output feedback MPC based on smoothed projected kinky inference. IET Control Theory Appl. 2019; 13(6): 795-805.
10.1049/iet-cta.2018.5522
Web of Science® Google Scholar
19Manzano JM, Limon D, Muñoz de la Peña D, Calliess J-P. Robust learning-based MPC for nonlinear constrained systems. Automatica. 2020; 117:108948.
10.1016/j.automatica.2020.108948
Web of Science® Google Scholar
20Mitchell TM. Machine learning and data mining. Commun ACM. 1999; 42(11): 30-36.
10.1145/319382.319388
Web of Science® Google Scholar
21Di Cairano S, Bernardini D, Bemporad A, Kolmanovsky IV. Stochastic MPC with learning for driver-predictive vehicle control and its application to HEV energy management. IEEE Trans Control Systems Technol. 2013; 22(3): 1018-1031.
10.1109/TCST.2013.2272179
Web of Science® Google Scholar
22Ostafew CJ, Schoellig AP, Barfoot TD, Collier J. Learning-based nonlinear model predictive control to improve vision-based mobile robot path tracking. J Field Robot. 2016; 33(1): 133-152.
10.1002/rob.21587
Web of Science® Google Scholar
23Aswani A, Gonzalez H, Sastry SS, Tomlin C. Provably safe and robust learning-based model predictive control. Automatica. 2013; 49(5): 1216-1226.
10.1016/j.automatica.2013.02.003
Web of Science® Google Scholar
24Limon D, Calliess J, Maciejowski JM. Learning-based nonlinear model predictive control. IFAC-PapersOnLine. 2017; 50(1): 7769-7776.
10.1016/j.ifacol.2017.08.1050
Google Scholar
25Levin AU, Narendra KS. Identification of Nonlinear Dynamical Systems Using Neural Networks. Amsterdam, Netherlands: Elsevier; 1997: 129-160.
Google Scholar
26 Limon D, Alamo T, Raimondo DM, et al. Input-to-state stability: an unifying framework for robust model predictive control. Nonlinear Model Predictive Control. Berlin, Heidelberg: Springer; 2008.
Google Scholar
27 Rawlings JB, Mayne DQ. Model Predictive Control: Theory and Design. 1st ed. Madison, Wisconsin: Nob-Hill Publishing; 2009.
Google Scholar
28Limon D, Alamo T, Salas F, Camacho EF. On the stability of MPC without terminal constraint. IEEE Trans Automat Control. 2006; 42: 832-836.
10.1109/TAC.2006.875014
Web of Science® Google Scholar
29Johansson KH. The quadruple-tank process. IEEE Trans Control Syst Technol. 2000; 8: 456-465.
10.1109/87.845876
Web of Science® Google Scholar
30Rivera DE, Jun KS. An integrated identification and control design methodology for multivariable process system applications. IEEE Control Syst. 2000; 20(3): 25-37.
10.1109/37.845036
Web of Science® Google Scholar

Citing Literature

Volume31, Issue18

Special Issue:Adaptive and Learning‐based Model Predictive Control

December 2021

Pages 8813-8829

Online learning constrained model predictive control based on double prediction

Summary

REFERENCES

Citing Literature

References

Information

About Wiley Online Library

Help & Support

Opportunities

Connect with Wiley

Online learning constrained model predictive control based on double prediction

Summary

REFERENCES

Citing Literature

References

Related

Information