Total Energy Shaping with Neural Interconnection and Damping Assignment - Passivity Based Control

Santiago Sanchez-Escalonilla Plaza, Rodolfo Reyes-Baez, Bayu Jayawardhana
Proceedings of The 4th Annual Learning for Dynamics and Control Conference, PMLR 168:520-531, 2022.

Abstract

In this work we exploit the universal approximation property of Neural Networks (NNs) to design interconnection and damping assignment (IDA) passivity-based control (PBC) schemes for fully-actuated mechanical systems in the port-Hamiltonian (pH) framework. To that end, we transform the IDA-PBC method into a supervised learning problem that solves the partial differential matching equations, and fulfills equilibrium assignment and Lyapunov stability conditions. A main consequence of this, is that the output of the learning algorithm has a clear control-theoretic interpretation in terms of passivity and Lyapunov stability.The proposed control design methodology is validated for mechanical systems of one and two degrees-of-freedom via numerical simulations.

Cite this Paper

BibTeX
@InProceedings{pmlr-v168-plaza22a, title = {Total Energy Shaping with Neural Interconnection and Damping Assignment - Passivity Based Control}, author = {Plaza, Santiago Sanchez-Escalonilla and Reyes-Baez, Rodolfo and Jayawardhana, Bayu}, booktitle = {Proceedings of The 4th Annual Learning for Dynamics and Control Conference}, pages = {520--531}, 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/plaza22a/plaza22a.pdf}, url = {https://proceedings.mlr.press/v168/plaza22a.html}, abstract = {In this work we exploit the universal approximation property of Neural Networks (NNs) to design interconnection and damping assignment (IDA) passivity-based control (PBC) schemes for fully-actuated mechanical systems in the port-Hamiltonian (pH) framework. To that end, we transform the IDA-PBC method into a supervised learning problem that solves the partial differential matching equations, and fulfills equilibrium assignment and Lyapunov stability conditions. A main consequence of this, is that the output of the learning algorithm has a clear control-theoretic interpretation in terms of passivity and Lyapunov stability.The proposed control design methodology is validated for mechanical systems of one and two degrees-of-freedom via numerical simulations.} }
Endnote
%0 Conference Paper %T Total Energy Shaping with Neural Interconnection and Damping Assignment - Passivity Based Control %A Santiago Sanchez-Escalonilla Plaza %A Rodolfo Reyes-Baez %A Bayu Jayawardhana %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-plaza22a %I PMLR %P 520--531 %U https://proceedings.mlr.press/v168/plaza22a.html %V 168 %X In this work we exploit the universal approximation property of Neural Networks (NNs) to design interconnection and damping assignment (IDA) passivity-based control (PBC) schemes for fully-actuated mechanical systems in the port-Hamiltonian (pH) framework. To that end, we transform the IDA-PBC method into a supervised learning problem that solves the partial differential matching equations, and fulfills equilibrium assignment and Lyapunov stability conditions. A main consequence of this, is that the output of the learning algorithm has a clear control-theoretic interpretation in terms of passivity and Lyapunov stability.The proposed control design methodology is validated for mechanical systems of one and two degrees-of-freedom via numerical simulations.
APA
Plaza, S.S., Reyes-Baez, R. & Jayawardhana, B.. (2022). Total Energy Shaping with Neural Interconnection and Damping Assignment - Passivity Based Control. Proceedings of The 4th Annual Learning for Dynamics and Control Conference, in Proceedings of Machine Learning Research 168:520-531 Available from https://proceedings.mlr.press/v168/plaza22a.html.

Related Material