# Networked Online Learning for Control of Safety-Critical Resource-Constrained Systems based on Gaussian Processes

arXiv: https://arxiv.org/abs/2202.11491 · HTML: https://mlsanity.com/paper/2202.11491/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 18 references that are in the map.
- First posted on arXiv 23 Feb 2022.

## Builds on (most cited first, 7 of 7)

- [Distributed Gaussian Processes](https://mlsanity.com/paper/1502.02843/) (2015)
- [Uniform Error Bounds for Gaussian Process Regression with Application to Safe Control](https://mlsanity.com/paper/1906.01376/) (2019)
- [Streaming Sparse Gaussian Process Approximations](https://mlsanity.com/paper/1705.07131/) (2017)
- [Feedback Linearization based on Gaussian Processes with event-triggered Online Learning](https://mlsanity.com/paper/1911.06565/) (2019)
- [Posterior Variance Analysis of Gaussian Processes with Application to Average Learning Curves](https://mlsanity.com/paper/1906.01404/) (2019)
- [L1-GP: L1 Adaptive Control with Bayesian Learning](https://mlsanity.com/paper/2004.14594/) (2020)
- [How Training Data Impacts Performance in Learning-based Control](https://mlsanity.com/paper/2005.12062/) (2020)

## Built on by (most cited first, 2 of 2)

- [Learning-based Control for PMSM Using Distributed Gaussian Processes with Optimal Aggregation Strategy](https://mlsanity.com/paper/2307.13945/) (2023)
- [VeriCompress: A Tool to Streamline the Synthesis of Verified Robust Compressed Neural Networks from Scratch](https://mlsanity.com/paper/2211.09945/) (2022)

## Abstract (arXiv)

Safety-critical technical systems operating in unknown environments require the ability to quickly adapt their behavior, which can be achieved in control by inferring a model online from the data stream generated during operation. Gaussian process-based learning is particularly well suited for safety-critical applications as it ensures bounded prediction errors. While there exist computationally efficient approximations for online inference, these approaches lack guarantees for the prediction error and have high memory requirements, and are therefore not applicable to safety-critical systems with tight memory constraints. In this work, we propose a novel networked online learning approach based on Gaussian process regression, which addresses the issue of limited local resources by employing remote data management in the cloud. Our approach formally guarantees a bounded tracking error with high probability, which is exploited to identify the most relevant data to achieve a certain control performance. We further propose an effective data transmission scheme between the local system and the cloud taking bandwidth limitations and time delay of the transmission channel into account. The effectiveness of the proposed method is successfully demonstrated in a simulation.