Bounding the Difference Between Model Predictive Control and Neural Networks

Ross Drummond, Stephen Duncan, Mathew Turner, Patricia Pauli, Frank Allgower
Proceedings of The 4th Annual Learning for Dynamics and Control Conference, PMLR 168:817-829, 2022.

Abstract

There is a growing debate on whether the future of feedback control systems will be dominated by data-driven or model-driven approaches. Each of these two approaches has their own complimentary set of advantages and disadvantages, however, only limited attempts have, so far, been developed to bridge the gap between them. To address this issue, this paper introduces a method to bound the worst-case error between feedback control policies based upon model predictive control (MPC) and neural networks (NNs). This result is leveraged into an approach to automatically synthesize MPC policies minimising the worst-case error with respect to a NN. Numerical examples highlight the application of the bounds, with the goal of the paper being to encourage a more quantitative understanding of the relationship between data-driven and model-driven control.

Cite this Paper

BibTeX
@InProceedings{pmlr-v168-drummond22a, title = {Bounding the Difference Between Model Predictive Control and Neural Networks}, author = {Drummond, Ross and Duncan, Stephen and Turner, Mathew and Pauli, Patricia and Allgower, Frank}, booktitle = {Proceedings of The 4th Annual Learning for Dynamics and Control Conference}, pages = {817--829}, year = {2022}, editor = {Firoozi, Roya and Mehr, Negar and Yel, Esen and Antonova, Rika and Bohg, Jeannette and Schwager, Mac and Kochenderfer, Mykel}, volume = {168}, series = {Proceedings of Machine Learning Research}, month = {23--24 Jun}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v168/drummond22a/drummond22a.pdf}, url = {https://proceedings.mlr.press/v168/drummond22a.html}, abstract = {There is a growing debate on whether the future of feedback control systems will be dominated by data-driven or model-driven approaches. Each of these two approaches has their own complimentary set of advantages and disadvantages, however, only limited attempts have, so far, been developed to bridge the gap between them. To address this issue, this paper introduces a method to bound the worst-case error between feedback control policies based upon model predictive control (MPC) and neural networks (NNs). This result is leveraged into an approach to automatically synthesize MPC policies minimising the worst-case error with respect to a NN. Numerical examples highlight the application of the bounds, with the goal of the paper being to encourage a more quantitative understanding of the relationship between data-driven and model-driven control. } }
Endnote
%0 Conference Paper %T Bounding the Difference Between Model Predictive Control and Neural Networks %A Ross Drummond %A Stephen Duncan %A Mathew Turner %A Patricia Pauli %A Frank Allgower %B Proceedings of The 4th Annual Learning for Dynamics and Control Conference %C Proceedings of Machine Learning Research %D 2022 %E Roya Firoozi %E Negar Mehr %E Esen Yel %E Rika Antonova %E Jeannette Bohg %E Mac Schwager %E Mykel Kochenderfer %F pmlr-v168-drummond22a %I PMLR %P 817--829 %U https://proceedings.mlr.press/v168/drummond22a.html %V 168 %X There is a growing debate on whether the future of feedback control systems will be dominated by data-driven or model-driven approaches. Each of these two approaches has their own complimentary set of advantages and disadvantages, however, only limited attempts have, so far, been developed to bridge the gap between them. To address this issue, this paper introduces a method to bound the worst-case error between feedback control policies based upon model predictive control (MPC) and neural networks (NNs). This result is leveraged into an approach to automatically synthesize MPC policies minimising the worst-case error with respect to a NN. Numerical examples highlight the application of the bounds, with the goal of the paper being to encourage a more quantitative understanding of the relationship between data-driven and model-driven control.
APA
Drummond, R., Duncan, S., Turner, M., Pauli, P. & Allgower, F.. (2022). Bounding the Difference Between Model Predictive Control and Neural Networks. Proceedings of The 4th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 168:817-829 Available from https://proceedings.mlr.press/v168/drummond22a.html.

Related Material