Details
| Originalsprache | Englisch |
|---|---|
| Seiten (von - bis) | 1390-1402 |
| Seitenumfang | 13 |
| Fachzeitschrift | IEEE Transactions on Control Systems Technology |
| Jahrgang | 30 |
| Ausgabenummer | 4 |
| Publikationsstatus | Veröffentlicht - 1 Juli 2022 |
| Extern publiziert | Ja |
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.
ASJC Scopus Sachgebiete
- Ingenieurwesen (insg.)
- Steuerungs- und Systemtechnik
- Ingenieurwesen (insg.)
- Elektrotechnik und Elektronik
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: IEEE Transactions on Control Systems Technology, Jahrgang 30, Nr. 4, 01.07.2022, S. 1390-1402.
Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review
}
TY - JOUR
T1 - Collective Iterative Learning Control
T2 - Exploiting Diversity in Multi-Agent Systems for Reference Tracking Tasks
AU - Meindl, Michael
AU - Molinari, Fabio
AU - Lehmann, Dustin
AU - Seel, Thomas
PY - 2022/7/1
Y1 - 2022/7/1
N2 - 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.
AB - 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.
KW - Autonomous systems
KW - collective intelligence
KW - cooperative systems
KW - iterative learning control (ILC)
UR - http://www.scopus.com/inward/record.url?scp=85133800829&partnerID=8YFLogxK
U2 - 10.1109/TCST.2021.3109646
DO - 10.1109/TCST.2021.3109646
M3 - Article
AN - SCOPUS:85133800829
VL - 30
SP - 1390
EP - 1402
JO - IEEE Transactions on Control Systems Technology
JF - IEEE Transactions on Control Systems Technology
SN - 1063-6536
IS - 4
ER -