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

被引:6
作者
Meindl, Michael [1 ]
Molinari, Fabio [2 ]
Lehmann, Dustin [2 ]
Seel, Thomas [3 ]
机构
[1] Hsch Karlsruhe, Embedded Mechatron Lab, D-76133 Karlsruhe, Germany
[2] Tech Univ Berlin, Control Syst Grp, D-10587 Berlin, Germany
[3] Friedrich Alexander Univ Erlangen Nurnberg, Dept Artificial Intelligence Biomed Engn, D-91052 Erlangen, Germany
关键词
Task analysis; Trajectory; Convergence; Robots; Asymptotic stability; Multi-agent systems; Collective intelligence; Autonomous systems; collective intelligence; cooperative systems; iterative learning control (ILC);
D O I
10.1109/TCST.2021.3109646
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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.
引用
收藏
页码:1390 / 1402
页数:13
相关论文
共 32 条
[1]  
Aguilera M., 2004, P 23 ACM S PRINC DIS, P328, DOI DOI 10.1145/1011767.1011816
[2]   BETTERING OPERATION OF ROBOTS BY LEARNING [J].
ARIMOTO, S ;
KAWAMURA, S ;
MIYAZAKI, F .
JOURNAL OF ROBOTIC SYSTEMS, 1984, 1 (02) :123-140
[3]   The Flight Assembled Architecture Installation COOPERATIVE CONSTRUCTION WITH FLYING MACHINES [J].
Augugliaro, Federico ;
Lupashin, Sergei ;
Hamer, Michael ;
Male, Cason ;
Hehn, Markus ;
Mueler, Mark W. ;
Wilman, Jan Sebastian ;
Gramazio, Fabio ;
Kohler, Matthias ;
D'Andrea, Rafaello .
IEEE CONTROL SYSTEMS MAGAZINE, 2014, 34 (04) :46-64
[4]   A survey of iterative learning control [J].
Bristow, Douglas A. ;
Tharayil, Marina ;
Alleyne, Andrew G. .
IEEE CONTROL SYSTEMS MAGAZINE, 2006, 26 (03) :96-114
[5]   Social learning in fishes: a review [J].
Brown, C ;
Laland, KN .
FISH AND FISHERIES, 2003, 4 (03) :280-288
[6]   Decentralised Collaborative Iterative Learning Control for MIMO Multi-Agent Systems [J].
Chen, Shangcheng ;
Freeman, Christopher T. .
2019 AMERICAN CONTROL CONFERENCE (ACC), 2019, :3352-3357
[7]   Consensus-based distributed cooperative learning control for a group of discrete-time nonlinear multi-agent systems using neural networks [J].
Chen, Weisheng ;
Hua, Shaoyong ;
Ge, Shuzhi Sam .
AUTOMATICA, 2014, 50 (09) :2254-2268
[8]   Iterative learning control with time-partitioned update for collaborative output tracking [J].
Devasia, Santosh .
AUTOMATICA, 2016, 69 :258-264
[9]   Multi-Agent Systems: A Survey [J].
Dorri, Ali ;
Kanhere, Salil S. ;
Jurdak, Raja .
IEEE ACCESS, 2018, 6 :28573-28593
[10]   Frequency-Domain Analysis of Robust Monotonic Convergence of Norm-Optimal Iterative Learning Control [J].
Ge, Xinyi ;
Stein, Jeffrey L. ;
Ersal, Tulga .
IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY, 2018, 26 (02) :637-651