Project Details
Projekt
Safe active learning control with Gaussian processes
Applicant
Professorin Dr.-Ing. Sandra Hirche
Subject Area
Automation, Mechatronics, Control Systems, Intelligent Technical Systems, Robotics
Term
since 2025
Project identifier
Deutsche Forschungsgemeinschaft (DFG) - Project number 535860958
This project is part of the research unit "Active Learning for Systems and Control (ALeSCo) – Data Informativity, Uncertainty, and Guarantees". Active learning, the targeted acquisition of informative training data, is a highly relevant yet under-explored topic in the modeling and control of uncertain complex dynamical systems. The active learning concept has significant application potential in various domains such as autonomous robotics and energy systems. The primary objective of this project is to develop a novel framework for safe active learning in Gaussian process (GP) models used in learning-based control. GP regression offers a highly flexible machine learning method for learning nonlinear functions - specifically, uncertain dynamics - based on training data. It provides a principled approach to uncertainty quantification, which is crucial for ensuring robust guarantees. We will explore different notions of safety, including robust convergence and forward invariance. The main innovation of this project is the focus on active learning for control, which necessitates a different strategy from existing active learning methods for function regression, as indicated by our preliminary results. To this end, we will develop novel control-oriented data informativity measures, which will be used for exploration with guaranteed improvement rates in control performance. Additionally, computational aspects will be investigated. The developed algorithms will undergo theoretical analysis concerning robust control guarantees, learning rates, and uncertainty complexity trade-offs. Furthermore, they will be evaluated in the benchmark problems developed within the Research Unit ALeSCo.
DFG Programme
Research Units
