Intelligent Multi-agent Coordination and Learning

Chang, Y-C; Dostovalova, A; Lin, C-T; Kim, J

Intelligent Multi-agent Coordination and Learning

Chang, Y-C Dostovalova, A Lin, C-T Kim, J

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), 2019
Issue Date:: 2019-10

Closed Access

	Filename	Description	Size
	08914071.pdf	Published version	2.36 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Chang, Y-C
dc.contributor.author	Dostovalova, A
dc.contributor.author	Lin, C-T
dc.contributor.author	Kim, J
dc.date	2019-10-06
dc.date.accessioned	2020-06-18T22:09:07Z
dc.date.available	2020-06-18T22:09:07Z
dc.date.issued	2019-10
dc.identifier.citation	2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), 2019
dc.identifier.isbn	978-1-7281-4569-3
dc.identifier.issn	1062-922X
dc.identifier.issn	2577-1655
dc.identifier.uri	http://hdl.handle.net/10453/141543
dc.description.abstract	We present a hierarchical neural-fuzzy system for precision coordination of multiple mobile agents for simultaneous arrival at their destination positions in a cluttered urban environment. We assume that each agent is equipped with a 2D scanning LiDAR to make movement decisions based on local distance and bearing information. Two solution approaches are considered and compared. Both of them are structured around a hierarchical arrangement of controller modules to enable synchronisation of the agents arrival times while avoiding collision with obstacles. The first approach is based on cascading SONFIN (Self-Organizing Neural Fuzzy Inference Network) controllers, and the second approach considers the use of an LSTM (Long ShortTerm Memory) recurrent neural network module alongside SONFIN modules. Parameters of all the controllers are optimised using the Particle Swarm optimization algorithm. A physics-based simulator, Webots, is used as a training and testing environment for the two learning models to facilitate the deployment of codes to hardware which will follow in the next phase of our research.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)
dc.relation.ispartof	IEEE International Conference on Systems, Man and Cybernetics
dc.relation.isbasedon	10.1109/smc.2019.8914071
dc.rights	© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.	en_US
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Intelligent Multi-agent Coordination and Learning
dc.type	Conference Proceeding
utslib.location.activity	Bari, Italy
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2020-06-18T22:09:01Z
pubs.finish-date	2019-10-09
pubs.place-of-publication	Piscataway, USA
pubs.publication-status	Published
pubs.start-date	2019-10-06
dc.location	Piscataway, USA

Abstract:

We present a hierarchical neural-fuzzy system for precision coordination of multiple mobile agents for simultaneous arrival at their destination positions in a cluttered urban environment. We assume that each agent is equipped with a 2D scanning LiDAR to make movement decisions based on local distance and bearing information. Two solution approaches are considered and compared. Both of them are structured around a hierarchical arrangement of controller modules to enable synchronisation of the agents arrival times while avoiding collision with obstacles. The first approach is based on cascading SONFIN (Self-Organizing Neural Fuzzy Inference Network) controllers, and the second approach considers the use of an LSTM (Long ShortTerm Memory) recurrent neural network module alongside SONFIN modules. Parameters of all the controllers are optimised using the Particle Swarm optimization algorithm. A physics-based simulator, Webots, is used as a training and testing environment for the two learning models to facilitate the deployment of codes to hardware which will follow in the next phase of our research.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/141543