Saliency Based Control in Random Feature Networks

TL;DR

This paper introduces a novel feedback control approach using randomly perceived features, inspired by animal attention mechanisms, and explores the theoretical concepts of random channel controllability and observability in control systems.

Contribution

It proposes a new control framework based on random feature perception and introduces the theoretical concepts of random channel controllability and observability.

Findings

Introduces the concepts of random channel controllability and observability.

Establishes connections with networked control systems and communication protocols.

Provides theoretical analysis of control using random features.

Abstract

The ability to rapidly focus attention and react to salient environmental features enables animals to move agiley through their habitats. To replicate this kind of high-performance control of movement in synthetic systems, we propose a new approach to feedback control that bases control actions on randomly perceived features. Connections will be made with recent work incorporating communication protocols into networked control systems. The concepts of {\em random channel controllability} and {\em random channel observability} for LTI control systems are introduced and studied.