Journal
IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY
Volume 30, Issue 4, Pages 1390-1402Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCST.2021.3109646
Keywords
Task analysis; Trajectory; Convergence; Robots; Asymptotic stability; Multi-agent systems; Collective intelligence; Autonomous systems; collective intelligence; cooperative systems; iterative learning control (ILC)
Funding
- Deutsche Forschungsgemeinschaft (DFG), German Research Foundation [EXC 2002/1, 390523135, SPP1914, RA516/12-1]
- Verbund der Stifter through the Project Robotic Zoo
Ask authors/readers for more resources
Multi-agent systems can autonomously learn new tasks by combining individual and collective intelligence. The proposed novel collective learning control method combines ILC with a collective update strategy, allowing the group to overcome trade-offs and limitations of single-agent ILC through designing a heterogeneous collective. The theoretical results are confirmed through simulations and experiments with TWIPRs.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available