EUVIMEDEUVIMED entdecken
Crossref

Active Learning of Discrete-Time Dynamics for Uncertainty-Aware Model Predictive Control

Alessandro Saviolo, Jonathan Frey, Abhishek Rathod, Moritz Diehl, Giuseppe Loianno

IEEE Transactions on Robotics · 2024 · 40 · 1273-1291

DOI: 10.1109/tro.2023.3339543 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Robotics, 2024. Verfasst von Alessandro Saviolo und 4 weiteren Autor:innen. Die Arbeit wurde bisher 60-mal zitiert (Crossref) und nennt 87 Literaturangaben. Gefördert von: NSF CAREER, DARPA YFA, Qualcomm Research, in part by Nokia.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Model-based control requires an accurate model of the system dynamics for precisely and safely controlling the robot in complex and dynamic environments. Moreover, in presence of variations in the operating conditions, the model should be continuously refined to compensate for dynamics changes. In this article, we present a self-supervised learning approach that actively models the dynamics of nonlinear robotic systems. We combine offline learning from past experience and online learning from current robot interaction with the unknown environment. These two ingredients enable a highly sample-efficient and adaptive learning process, capable of accurately inferring model dynamics in real-time even in operating regimes that greatly differ from the training distribution. Moreover, we design an uncertainty-aware model predictive controller that is heuristically conditioned to the aleatoric (data) uncertainty of the learned dynamics. This controller actively chooses the optimal control actions that i) optimize the control performance, and ii) improve the efficiency of online learning sample collection. We demonstrate the effectiveness of our method through a series of challenging real-world experiments using a quadrotor system. Our approach showcases high resilience and generalization capabilities by consistently adapting to unseen flight conditions, while it significantly outperforms classical and adaptive control baselines.11Video: https://youtu.be/QmEhSTcWob4

Förderung

  • NSF CAREER
  • DARPA YFA
  • Qualcomm Research, in part by Nokia
  • NYU Wireless

Zitieren

APA

Saviolo, A., Frey, J., Rathod, A., Diehl, M., & Loianno, G. (2024). Active Learning of Discrete-Time Dynamics for Uncertainty-Aware Model Predictive Control. IEEE Transactions on Robotics, 40, 1273-1291. https://doi.org/10.1109/tro.2023.3339543

Vancouver

Saviolo A, Frey J, Rathod A, Diehl M, Loianno G. Active Learning of Discrete-Time Dynamics for Uncertainty-Aware Model Predictive Control. IEEE Transactions on Robotics. 2024;40:1273-1291. doi:10.1109/tro.2023.3339543

BibTeX
@article{Saviolo2024,
  author = {Saviolo, Alessandro and Frey, Jonathan and Rathod, Abhishek and Diehl, Moritz and Loianno, Giuseppe},
  title = {Active Learning of Discrete-Time Dynamics for Uncertainty-Aware Model Predictive Control},
  journal = {IEEE Transactions on Robotics},
  year = {2024},
  volume = {40},
  pages = {1273--1291},
  doi = {10.1109/tro.2023.3339543}
}
Kostenlos starten →