Collective Iterative Learning Control: Exploiting Diversity in Multi-Agent Systems for Reference Tracking Tasks

TL;DR

This paper introduces a novel collective iterative learning control method for multi-agent systems, enabling agents to collaboratively learn reference tracking tasks efficiently by leveraging diverse individual strategies and collective intelligence.

Contribution

It proposes a new collective learning control approach combining ILC with a collective update, allowing heterogeneous agents to overcome single-agent limitations.

Findings

The method achieves desirable convergence properties.

Simulations and experiments validate improved learning performance.

Heterogeneous agents enhance collective learning efficiency.

Abstract

Multi-agent systems (MASs) can autonomously learn to solve previously unknown tasks by means of each agent's individual intelligence as well as by collaborating and exploiting collective intelligence. This article considers a group of autonomous agents learning to track the same given reference trajectory in a possibly small number of trials. We propose a novel collective learning control method that combines iterative learning control (ILC) with a collective update strategy. We derive conditions for desirable convergence properties of such systems. We show that the proposed method allows the collective to combine the advantages of the agents' individual learning strategies and thereby overcomes trade-offs and limitations of single-agent ILC. This benefit is achieved by designing a heterogeneous collective, i.e., a different learning law is assigned to each agent. All theoretical results are confirmed in simulations and experiments with two-wheeled-inverted-pendulum robots (TWIPRs) that jointly learn to perform the desired maneuver.