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

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

Research output: Contribution to journalArticlepeer-review

Abstract

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

Original languageEnglish (US)
Pages (from-to)1273-1291
Number of pages19
JournalIEEE Transactions on Robotics
Volume40
DOIs
StatePublished - 2024

Keywords

  • Model learning for control
  • aerial systems
  • learning and adaptive systems
  • mechanics and control
  • optimization and optimal control

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Active Learning of Discrete-Time Dynamics for Uncertainty-Aware Model Predictive Control'. Together they form a unique fingerprint.

Cite this