Hierarchical Event-Triggered Systems: Safe Learning of Quasi-Optimal Deadline Policies

TL;DR

This paper introduces a hierarchical event-triggered control architecture combining reinforcement learning and traditional control to optimize long-term resource efficiency while ensuring safety, demonstrated on spacecraft control.

Contribution

It proposes a novel hierarchical framework with a deadline policy learned via reinforcement learning to enhance event-triggered control efficiency.

Findings

Reduced actuation frequency compared to standard ETC

Maintained safety guarantees during control

Effective long-term resource optimization

Abstract

We present a hierarchical architecture to improve the efficiency of event-triggered control (ETC) in reducing resource consumption. This paper considers event-triggered systems generally as an impulsive control system in which the objective is to minimize the number of impulses. Our architecture recognizes that traditional ETC is a greedy strategy towards optimizing average inter-event times and introduces the idea of a deadline policy for the optimization of long-term discounted inter-event times. A lower layer is designed employing event-triggered control to guarantee the satisfaction of control objectives, while a higher layer implements a deadline policy designed with reinforcement learning to improve the discounted inter-event time. We apply this scheme to the control of an orbiting spacecraft, showing superior performance in terms of actuation frequency reduction with respect to a standard (one-layer) ETC while maintaining safety guarantees.