Online Dynamics Learning for Predictive Control with an Application to Aerial Robots

Tom Z. Jiahao, Kong Yao Chee, M. Ani Hsieh
Proceedings of The 6th Conference on Robot Learning, PMLR 205:2251-2261, 2023.

Abstract

In this work, we consider the task of improving the accuracy of dynamic models for model predictive control (MPC) in an online setting. Although prediction models can be learned and applied to model-based controllers, these models are often learned offline. In this offline setting, training data is first collected and a prediction model is learned through an elaborated training procedure. However, since the model is learned offline, it does not adapt to disturbances or model errors observed during deployment. To improve the adaptiveness of the model and the controller, we propose an online dynamics learning framework that continually improves the accuracy of the dynamic model during deployment. We adopt knowledge-based neural ordinary differential equations (KNODE) as the dynamic models, and use techniques inspired by transfer learning to continually improve the model accuracy. We demonstrate the efficacy of our framework with a quadrotor, and verify the framework in both simulations and physical experiments. Results show that our approach can account for disturbances that are possibly time-varying, while maintaining good trajectory tracking performance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v205-jiahao23a, title = {Online Dynamics Learning for Predictive Control with an Application to Aerial Robots}, author = {Jiahao, Tom Z. and Chee, Kong Yao and Hsieh, M. Ani}, booktitle = {Proceedings of The 6th Conference on Robot Learning}, pages = {2251--2261}, year = {2023}, editor = {Liu, Karen and Kulic, Dana and Ichnowski, Jeff}, volume = {205}, series = {Proceedings of Machine Learning Research}, month = {14--18 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v205/jiahao23a/jiahao23a.pdf}, url = {https://proceedings.mlr.press/v205/jiahao23a.html}, abstract = {In this work, we consider the task of improving the accuracy of dynamic models for model predictive control (MPC) in an online setting. Although prediction models can be learned and applied to model-based controllers, these models are often learned offline. In this offline setting, training data is first collected and a prediction model is learned through an elaborated training procedure. However, since the model is learned offline, it does not adapt to disturbances or model errors observed during deployment. To improve the adaptiveness of the model and the controller, we propose an online dynamics learning framework that continually improves the accuracy of the dynamic model during deployment. We adopt knowledge-based neural ordinary differential equations (KNODE) as the dynamic models, and use techniques inspired by transfer learning to continually improve the model accuracy. We demonstrate the efficacy of our framework with a quadrotor, and verify the framework in both simulations and physical experiments. Results show that our approach can account for disturbances that are possibly time-varying, while maintaining good trajectory tracking performance.} }
Endnote
%0 Conference Paper %T Online Dynamics Learning for Predictive Control with an Application to Aerial Robots %A Tom Z. Jiahao %A Kong Yao Chee %A M. Ani Hsieh %B Proceedings of The 6th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Karen Liu %E Dana Kulic %E Jeff Ichnowski %F pmlr-v205-jiahao23a %I PMLR %P 2251--2261 %U https://proceedings.mlr.press/v205/jiahao23a.html %V 205 %X In this work, we consider the task of improving the accuracy of dynamic models for model predictive control (MPC) in an online setting. Although prediction models can be learned and applied to model-based controllers, these models are often learned offline. In this offline setting, training data is first collected and a prediction model is learned through an elaborated training procedure. However, since the model is learned offline, it does not adapt to disturbances or model errors observed during deployment. To improve the adaptiveness of the model and the controller, we propose an online dynamics learning framework that continually improves the accuracy of the dynamic model during deployment. We adopt knowledge-based neural ordinary differential equations (KNODE) as the dynamic models, and use techniques inspired by transfer learning to continually improve the model accuracy. We demonstrate the efficacy of our framework with a quadrotor, and verify the framework in both simulations and physical experiments. Results show that our approach can account for disturbances that are possibly time-varying, while maintaining good trajectory tracking performance.
APA
Jiahao, T.Z., Chee, K.Y. & Hsieh, M.A.. (2023). Online Dynamics Learning for Predictive Control with an Application to Aerial Robots. Proceedings of The 6th Conference on Robot Learning, in Proceedings of Machine Learning Research 205:2251-2261 Available from https://proceedings.mlr.press/v205/jiahao23a.html.

Related Material