Learning supported Model Predictive Control for Tracking of Periodic References

Janine Matschek, Rolf Findeisen
Proceedings of the 2nd Conference on Learning for Dynamics and Control, PMLR 120:511-520, 2020.

Abstract

Increased autonomy of controllers in tasks with uncertainties stemming from the interaction with the environment can be achieved by incorporation of learning. Examples are control tasks where the system should follow a reference which depends on measurement data from surrounding systems as e.g. humans or other control systems. We propose a learning strategy for Gaussian processes to model, filter and predict references for control systems under model predictive control. Hereby constraints in the learning are included to achieve safety guarantees as trackability and recursive feasibility. An illustrative simulation example for motion compensation is given which shows performance improvements of combined constrained learning and predictive control besides the provided guarantees.

Cite this Paper

BibTeX
@InProceedings{pmlr-v120-matschek20a, title = {Learning supported Model Predictive Control for Tracking of Periodic References}, author = {Matschek, Janine and Findeisen, Rolf}, booktitle = {Proceedings of the 2nd Conference on Learning for Dynamics and Control}, pages = {511--520}, year = {2020}, editor = {Bayen, Alexandre M. and Jadbabaie, Ali and Pappas, George and Parrilo, Pablo A. and Recht, Benjamin and Tomlin, Claire and Zeilinger, Melanie}, volume = {120}, series = {Proceedings of Machine Learning Research}, month = {10--11 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v120/matschek20a/matschek20a.pdf}, url = {https://proceedings.mlr.press/v120/matschek20a.html}, abstract = {Increased autonomy of controllers in tasks with uncertainties stemming from the interaction with the environment can be achieved by incorporation of learning. Examples are control tasks where the system should follow a reference which depends on measurement data from surrounding systems as e.g. humans or other control systems. We propose a learning strategy for Gaussian processes to model, filter and predict references for control systems under model predictive control. Hereby constraints in the learning are included to achieve safety guarantees as trackability and recursive feasibility. An illustrative simulation example for motion compensation is given which shows performance improvements of combined constrained learning and predictive control besides the provided guarantees.} }
Endnote
%0 Conference Paper %T Learning supported Model Predictive Control for Tracking of Periodic References %A Janine Matschek %A Rolf Findeisen %B Proceedings of the 2nd Conference on Learning for Dynamics and Control %C Proceedings of Machine Learning Research %D 2020 %E Alexandre M. Bayen %E Ali Jadbabaie %E George Pappas %E Pablo A. Parrilo %E Benjamin Recht %E Claire Tomlin %E Melanie Zeilinger %F pmlr-v120-matschek20a %I PMLR %P 511--520 %U https://proceedings.mlr.press/v120/matschek20a.html %V 120 %X Increased autonomy of controllers in tasks with uncertainties stemming from the interaction with the environment can be achieved by incorporation of learning. Examples are control tasks where the system should follow a reference which depends on measurement data from surrounding systems as e.g. humans or other control systems. We propose a learning strategy for Gaussian processes to model, filter and predict references for control systems under model predictive control. Hereby constraints in the learning are included to achieve safety guarantees as trackability and recursive feasibility. An illustrative simulation example for motion compensation is given which shows performance improvements of combined constrained learning and predictive control besides the provided guarantees.
APA
Matschek, J. & Findeisen, R.. (2020). Learning supported Model Predictive Control for Tracking of Periodic References. Proceedings of the 2nd Conference on Learning for Dynamics and Control, in Proceedings of Machine Learning Research 120:511-520 Available from https://proceedings.mlr.press/v120/matschek20a.html.

Related Material