A Lifting Approach to Learning-Based Self-Triggered Control with Gaussian Processes

TL;DR

This paper introduces a novel lifting method combined with Gaussian process regression to design self-triggered control for unknown networked control systems, optimizing control and communication policies efficiently.

Contribution

It proposes a new lifting approach that models inter-event times as inputs, enabling Gaussian process learning and gradient-based policy optimization for self-triggered control.

Findings

Effective control and communication policy learned

Numerical simulations demonstrate approach's efficiency

Lifting approach improves handling of unknown system dynamics

Abstract

This paper investigates the design of self-triggered control for networked control systems (NCS), where the dynamics of the plant is unknown apriori. To deal with the nature of the self-triggered control, in which state measurements are transmitted to the controller a-periodically, we propose to lift the continuous-time dynamics to a novel dynamical model by taking an inter-event time as an additional input, and then, the lifted model is learned by the Gaussian processes (GP) regression. Moreover, we propose a learning-based approach, in which a self-triggered controller is learned by minimizing a cost function, such that it can take inter-sample behavior into account. By employing the lifting approach, we can utilize a gradient-based policy update as an efficient method to optimize both control and communication policies. Finally, we summarize the overall algorithm and provide a numerical simulation to illustrate the effectiveness of the proposed approach.