Inverse optimal control as an errors-in-variables problem

Rahel Rickenbach, Anna Scampicchio, Melanie N. Zeilinger
Proceedings of the 6th Annual Learning for Dynamics & Control Conference, PMLR 242:375-386, 2024.

Abstract

Inverse optimal control (IOC) is about estimating an unknown objective of interest given its optimal control sequence. However, truly optimal demonstrations are often difficult to obtain, e.g., due to human errors or inaccurate measurements. This paper presents an IOC framework for objective estimation from multiple sub-optimal demonstrations in constrained environments. It builds upon the Karush-Kuhn-Tucker optimality conditions, and addresses the Errors-In-Variables problem that emerges from the use of sub-optimal data. The approach presented is applied to various systems in simulation, and consistency guarantees are provided for linear systems with zero mean additive noise, polytopic constraints, and objectives with quadratic features.

Cite this Paper

BibTeX
@InProceedings{pmlr-v242-rickenbach24a, title = {Inverse optimal control as an errors-in-variables problem}, author = {Rickenbach, Rahel and Scampicchio, Anna and Zeilinger, Melanie N.}, booktitle = {Proceedings of the 6th Annual Learning for Dynamics & Control Conference}, pages = {375--386}, year = {2024}, editor = {Abate, Alessandro and Cannon, Mark and Margellos, Kostas and Papachristodoulou, Antonis}, volume = {242}, series = {Proceedings of Machine Learning Research}, month = {15--17 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v242/rickenbach24a/rickenbach24a.pdf}, url = {https://proceedings.mlr.press/v242/rickenbach24a.html}, abstract = {Inverse optimal control (IOC) is about estimating an unknown objective of interest given its optimal control sequence. However, truly optimal demonstrations are often difficult to obtain, e.g., due to human errors or inaccurate measurements. This paper presents an IOC framework for objective estimation from multiple sub-optimal demonstrations in constrained environments. It builds upon the Karush-Kuhn-Tucker optimality conditions, and addresses the Errors-In-Variables problem that emerges from the use of sub-optimal data. The approach presented is applied to various systems in simulation, and consistency guarantees are provided for linear systems with zero mean additive noise, polytopic constraints, and objectives with quadratic features.} }
Endnote
%0 Conference Paper %T Inverse optimal control as an errors-in-variables problem %A Rahel Rickenbach %A Anna Scampicchio %A Melanie N. Zeilinger %B Proceedings of the 6th Annual Learning for Dynamics & Control Conference %C Proceedings of Machine Learning Research %D 2024 %E Alessandro Abate %E Mark Cannon %E Kostas Margellos %E Antonis Papachristodoulou %F pmlr-v242-rickenbach24a %I PMLR %P 375--386 %U https://proceedings.mlr.press/v242/rickenbach24a.html %V 242 %X Inverse optimal control (IOC) is about estimating an unknown objective of interest given its optimal control sequence. However, truly optimal demonstrations are often difficult to obtain, e.g., due to human errors or inaccurate measurements. This paper presents an IOC framework for objective estimation from multiple sub-optimal demonstrations in constrained environments. It builds upon the Karush-Kuhn-Tucker optimality conditions, and addresses the Errors-In-Variables problem that emerges from the use of sub-optimal data. The approach presented is applied to various systems in simulation, and consistency guarantees are provided for linear systems with zero mean additive noise, polytopic constraints, and objectives with quadratic features.
APA
Rickenbach, R., Scampicchio, A. & Zeilinger, M.N.. (2024). Inverse optimal control as an errors-in-variables problem. Proceedings of the 6th Annual Learning for Dynamics & Control Conference, in Proceedings of Machine Learning Research 242:375-386 Available from https://proceedings.mlr.press/v242/rickenbach24a.html.

Related Material