Print Email Facebook Twitter Promises of Deep Kernel Learning for Control Synthesis Title Promises of Deep Kernel Learning for Control Synthesis Author Reed, Robert (University of Colorado) Laurenti, L. (TU Delft Team Luca Laurenti) Lahijanian, Morteza (University of Colorado) Date 2023 Abstract Deep Kernel Learning (DKL) combines the representational power of neural networks with the uncertainty quantification of Gaussian Processes. Hence, it is potentially a promising tool to learn and control complex dynamical systems. In this letter, we develop a scalable abstraction-based framework that enables the use of DKL for control synthesis of stochastic dynamical systems against complex specifications. Specifically, we consider temporal logic specifications and create an end-to-end framework that uses DKL to learn an unknown system from data and formally abstracts the DKL model into an interval Markov decision process to perform control synthesis with correctness guarantees. Furthermore, we identify a deep architecture that enables accurate learning and efficient abstraction computation. The effectiveness of our approach is illustrated on various benchmarks, including a 5-D nonlinear stochastic system, showing how control synthesis with DKL can substantially outperform state-of-the-art competitive methods. Subject Artificial neural networksControl systemsKernelMachine LearningRobust ControlScalabilityStochastic systemsStochastic SystemsTrajectoryUncertainty To reference this document use: http://resolver.tudelft.nl/uuid:7a0f3a04-48f2-4a65-8977-4df165431bf8 DOI https://doi.org/10.1109/LCSYS.2023.3340995 Embargo date 2024-06-08 ISSN 2475-1456 Source IEEE Control Systems Letters, 7, 3986-3991 Bibliographical note Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type journal article Rights © 2023 Robert Reed, L. Laurenti, Morteza Lahijanian Files PDF Promises_of_Deep_Kernel_L ... thesis.pdf 1.6 MB Close viewer /islandora/object/uuid:7a0f3a04-48f2-4a65-8977-4df165431bf8/datastream/OBJ/view