Proto-MPC: An encoder-prototype-decoder approach for quadrotor control in challenging winds

Yuliang Gu, Sheng Cheng, Naira Hovakimyan
Proceedings of the 6th Annual Learning for Dynamics & Control Conference, PMLR 242:1765-1776, 2024.

Abstract

Quadrotors are increasingly used in the evolving field of aerial robotics for their agility and mechanical simplicity. However, inherent uncertainties, such as aerodynamic effects coupled with quadrotors’ operation in dynamically changing environments, pose significant challenges for traditional, nominal model-based control designs. To address these challenges, we propose a multi-task meta-learning method called Encoder-Prototype-Decoder (EPD), which has the advantage of effectively balancing shared and distinctive representations across diverse training tasks. Subsequently, we integrate the EPD model into a model predictive control problem (Proto-MPC) to enhance the quadrotor’s ability to adapt and operate across a spectrum of dynamically changing tasks with an efficient online implementation. We validate the proposed method in simulations, which demonstrates Proto-MPC’s robust performance in trajectory tracking of a quadrotor being subject to static and spatially varying side winds.

Cite this Paper

BibTeX
@InProceedings{pmlr-v242-gu24a, title = {Proto-{MPC}: {A}n encoder-prototype-decoder approach for quadrotor control in challenging winds}, author = {Gu, Yuliang and Cheng, Sheng and Hovakimyan, Naira}, booktitle = {Proceedings of the 6th Annual Learning for Dynamics & Control Conference}, pages = {1765--1776}, 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/gu24a/gu24a.pdf}, url = {https://proceedings.mlr.press/v242/gu24a.html}, abstract = {Quadrotors are increasingly used in the evolving field of aerial robotics for their agility and mechanical simplicity. However, inherent uncertainties, such as aerodynamic effects coupled with quadrotors’ operation in dynamically changing environments, pose significant challenges for traditional, nominal model-based control designs. To address these challenges, we propose a multi-task meta-learning method called Encoder-Prototype-Decoder (EPD), which has the advantage of effectively balancing shared and distinctive representations across diverse training tasks. Subsequently, we integrate the EPD model into a model predictive control problem (Proto-MPC) to enhance the quadrotor’s ability to adapt and operate across a spectrum of dynamically changing tasks with an efficient online implementation. We validate the proposed method in simulations, which demonstrates Proto-MPC’s robust performance in trajectory tracking of a quadrotor being subject to static and spatially varying side winds.} }
Endnote
%0 Conference Paper %T Proto-MPC: An encoder-prototype-decoder approach for quadrotor control in challenging winds %A Yuliang Gu %A Sheng Cheng %A Naira Hovakimyan %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-gu24a %I PMLR %P 1765--1776 %U https://proceedings.mlr.press/v242/gu24a.html %V 242 %X Quadrotors are increasingly used in the evolving field of aerial robotics for their agility and mechanical simplicity. However, inherent uncertainties, such as aerodynamic effects coupled with quadrotors’ operation in dynamically changing environments, pose significant challenges for traditional, nominal model-based control designs. To address these challenges, we propose a multi-task meta-learning method called Encoder-Prototype-Decoder (EPD), which has the advantage of effectively balancing shared and distinctive representations across diverse training tasks. Subsequently, we integrate the EPD model into a model predictive control problem (Proto-MPC) to enhance the quadrotor’s ability to adapt and operate across a spectrum of dynamically changing tasks with an efficient online implementation. We validate the proposed method in simulations, which demonstrates Proto-MPC’s robust performance in trajectory tracking of a quadrotor being subject to static and spatially varying side winds.
APA
Gu, Y., Cheng, S. & Hovakimyan, N.. (2024). Proto-MPC: An encoder-prototype-decoder approach for quadrotor control in challenging winds. Proceedings of the 6th Annual Learning for Dynamics & Control Conference, in Proceedings of Machine Learning Research 242:1765-1776 Available from https://proceedings.mlr.press/v242/gu24a.html.

Related Material