Lagrangian inspired polynomial estimator for black-box learning and control of underactuated systems

Giulio Giacomuzzo, Riccardo Cescon, Diego Romeres, Ruggero Carli, Alberto Dalla Libera
Proceedings of the 6th Annual Learning for Dynamics & Control Conference, PMLR 242:1292-1304, 2024.

Abstract

The Lagrangian Inspired Polynomial (LIP) estimator (Giacomuzzo et al., 2023) is a black-box estimator based on Gaussian Process Regression, recently presented for the inverse dynamics identi- fication of Lagrangian systems. It relies on a novel multi-output kernel that embeds the structure of the Euler-Lagrange equation. In this work, we extend its analysis to the class of underactuated robots. First, we show that, despite being a black-box model, the LIP allows estimating kinetic and potential energies, as well as the inertial, Coriolis, and gravity components directly from the overall torque measures. Then we exploit these properties to derive a two-stage energy-based controller for the swing-up and stabilization of balancing robots. Experimental results on a simulated Pendubot confirm the feasibility of the proposed approach.

Cite this Paper

BibTeX
@InProceedings{pmlr-v242-giacomuzzo24a, title = {{L}agrangian inspired polynomial estimator for black-box learning and control of underactuated systems}, author = {Giacomuzzo, Giulio and Cescon, Riccardo and Romeres, Diego and Carli, Ruggero and Libera, Alberto Dalla}, booktitle = {Proceedings of the 6th Annual Learning for Dynamics & Control Conference}, pages = {1292--1304}, 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/giacomuzzo24a/giacomuzzo24a.pdf}, url = {https://proceedings.mlr.press/v242/giacomuzzo24a.html}, abstract = {The Lagrangian Inspired Polynomial (LIP) estimator (Giacomuzzo et al., 2023) is a black-box estimator based on Gaussian Process Regression, recently presented for the inverse dynamics identi- fication of Lagrangian systems. It relies on a novel multi-output kernel that embeds the structure of the Euler-Lagrange equation. In this work, we extend its analysis to the class of underactuated robots. First, we show that, despite being a black-box model, the LIP allows estimating kinetic and potential energies, as well as the inertial, Coriolis, and gravity components directly from the overall torque measures. Then we exploit these properties to derive a two-stage energy-based controller for the swing-up and stabilization of balancing robots. Experimental results on a simulated Pendubot confirm the feasibility of the proposed approach.} }
Endnote
%0 Conference Paper %T Lagrangian inspired polynomial estimator for black-box learning and control of underactuated systems %A Giulio Giacomuzzo %A Riccardo Cescon %A Diego Romeres %A Ruggero Carli %A Alberto Dalla Libera %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-giacomuzzo24a %I PMLR %P 1292--1304 %U https://proceedings.mlr.press/v242/giacomuzzo24a.html %V 242 %X The Lagrangian Inspired Polynomial (LIP) estimator (Giacomuzzo et al., 2023) is a black-box estimator based on Gaussian Process Regression, recently presented for the inverse dynamics identi- fication of Lagrangian systems. It relies on a novel multi-output kernel that embeds the structure of the Euler-Lagrange equation. In this work, we extend its analysis to the class of underactuated robots. First, we show that, despite being a black-box model, the LIP allows estimating kinetic and potential energies, as well as the inertial, Coriolis, and gravity components directly from the overall torque measures. Then we exploit these properties to derive a two-stage energy-based controller for the swing-up and stabilization of balancing robots. Experimental results on a simulated Pendubot confirm the feasibility of the proposed approach.
APA
Giacomuzzo, G., Cescon, R., Romeres, D., Carli, R. & Libera, A.D.. (2024). Lagrangian inspired polynomial estimator for black-box learning and control of underactuated systems. Proceedings of the 6th Annual Learning for Dynamics & Control Conference, in Proceedings of Machine Learning Research 242:1292-1304 Available from https://proceedings.mlr.press/v242/giacomuzzo24a.html.

Related Material