Episodic Gaussian Process-Based Learning Control with Vanishing Tracking Errors
Not on the map. Why?
Abstract (arXiv)
Due to the increasing complexity of technical systems, accurate first principle models can often not be obtained. Supervised machine learning can mitigate this issue by inferring models from measurement data. Gaussian process regression is particularly well suited for this purpose due to its high data-efficiency and its explicit uncertainty representation, which allows the derivation of prediction error bounds. These error bounds have been exploited to show tracking accuracy guarantees for a variety of control approaches, but their direct dependency on the training data is generally unclear. We address this issue by deriving a Bayesian prediction error bound for GP regression, which we show to decay with the growth of a novel, kernel-based measure of data density. Based on the prediction error bound, we prove time-varying tracking accuracy guarantees for learned GP models used as feedback compensation of unknown nonlinearities, and show to achieve vanishing tracking error with increasing data density. This enables us to develop an episodic approach for learning Gaussian process models, such that an arbitrary tracking accuracy can be guaranteed. The effectiveness of the derived theory is demonstrated in several simulations.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 65 references that are in the map. First posted on arXiv 10 Jul 2023.
Builds on
24 of 65 references.
References · 24
- 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 417
- 2017On Kernelized Multi-armed Banditscited by 348
- 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
- 2018Gaussian Processes and Kernel Methods: A Review on Connections and Equivalencescited by 188
- 2015Gaussian Processes for Data-Efficient Learning in Robotics and Controlcited by 97
- 2017Cautious Model Predictive Control using Gaussian Process Regressioncited by 91
- 2020Efficient Model-Based Reinforcement Learning through Optimistic Policy Search and Planningcited by 83
- 2015Safe Controller Optimization for Quadrotors with Gaussian Processescited by 77
- 2019Uniform Error Bounds for Gaussian Process Regression with Application to Safe Controlcited by 64
- 2021Practical and Rigorous Uncertainty Bounds for Gaussian Process Regressioncited by 49
- 2017Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimizationcited by 33
- 2019Actively Learning Gaussian Process Dynamicscited by 26
12 more
- 2019Feedback Linearization based on Gaussian Processes with event-triggered Online Learningcited by 24
- 2020Deterministic error bounds for kernel-based learning techniques under bounded noisecited by 24
- 2017Gaussian Process bandits with adaptive discretizationcited by 20
- 2020Control Barriers in Bayesian Learning of System Dynamicscited by 17
- 2021Gaussian Process Uniform Error Bounds with Unknown Hyperparameters for Safety-Critical Applicationscited by 17
- 2021Combining Pessimism with Optimism for Robust and Efficient Model-Based Deep Reinforcement Learningcited by 14
- 2021Robust Uncertainty Bounds in Reproducing Kernel Hilbert Spaces: A Convex Optimization Approachcited by 14
- 2018Provably Robust Learning-Based Approach for High-Accuracy Tracking Control of Lagrangian Systemscited by 9
- 2020Localized active learning of Gaussian process state space modelscited by 8
- 2020KPC: Learning-Based Model Predictive Control with Deterministic Guaranteescited by 5
- 2023Guarantees for data-driven control of nonlinear systems using semidefinite programming: A surveycited by 4
- 2021Learning-enhanced robust controller synthesis with rigorous statistical and control-theoretic guaranteescited by 2
Built on by
Not cited yet.