CoordiNet: Constrained Dynamics Learning for State Coordination over Graph

Niwa, K; Ueda, N; Sawada, H; Fujino, A; Takeda, S; Zhang, G; Kleijn, WB

CoordiNet: Constrained Dynamics Learning for State Coordination over Graph

Niwa, K Ueda, N Sawada, H Fujino, A Takeda, S Zhang, G

Kleijn, WB

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Transactions on Signal and Information Processing over Networks, 2023, 9, pp. 242-257
Issue Date:: 2023-01-01

In Progress

	Filename	Description	Size
	CoordiNet_Constrained_Dynamics_Learning_for_State_Coordination_Over_Graph.pdf	Published version	2.96 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is being processed and is not currently available.

Full metadata record

Field	Value	Language
dc.contributor.author	Niwa, K
dc.contributor.author	Ueda, N
dc.contributor.author	Sawada, H
dc.contributor.author	Fujino, A
dc.contributor.author	Takeda, S
dc.contributor.author	Zhang, G https://orcid.org/0000-0003-4521-542X
dc.contributor.author	Kleijn, WB
dc.date.accessioned	2024-04-10T23:23:23Z
dc.date.available	2024-04-10T23:23:23Z
dc.date.issued	2023-01-01
dc.identifier.citation	IEEE Transactions on Signal and Information Processing over Networks, 2023, 9, pp. 242-257
dc.identifier.issn	2373-776X
dc.identifier.issn	2373-776X
dc.identifier.uri	http://hdl.handle.net/10453/177697
dc.description.abstract	A neural architecture to efficiently coordinate the transitions of state variables (states) over a graph is proposed. We consider the coordination of the time evolution of the state variables associated with the nodes on a graph. The states are associated with physical attributes of agents, e.g., the speed and/or location of vehicles. Efficient coordination then corresponds to the optimization of dynamics (how fast do vehicles travel) that may be subject to constraints (travel must be collision-free). The aim of this paper is (i) the formulation of learnable constrained dynamics which governs the transition of states under constraints over a graph and (ii) to show its industrial application. Firstly, we formulate continuous ordinary differential equations (ODEs), namely forward propagation of state transitions over a graph and backward propagation to optimize model parameters for the learnable constrained dynamics. Discretization of these continuous ODEs results in the neural architecture CoordiNet. Secondly, as an application of CoordiNet, we address a traffic coordination problem by learning constrained dynamics such that vehicles can travel as fast as possible without collisions. Simulation experiments of traffic coordination confirm that our method maximizes the vehicles' speed states while avoiding collisions.
dc.language	English
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartof	IEEE Transactions on Signal and Information Processing over Networks
dc.relation.isbasedon	10.1109/TSIPN.2023.3248944
dc.rights	info:eu-repo/semantics/restrictedAccess
dc.subject.classification	4006 Communications engineering
dc.subject.classification	4606 Distributed computing and systems software
dc.subject.classification	4611 Machine learning
dc.title	CoordiNet: Constrained Dynamics Learning for State Coordination over Graph
dc.type	Journal Article
utslib.citation.volume	9
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
utslib.copyright.status	in_progress	*
dc.date.updated	2024-04-10T23:23:21Z
pubs.publication-status	Published
pubs.volume	9

Abstract:

A neural architecture to efficiently coordinate the transitions of state variables (states) over a graph is proposed. We consider the coordination of the time evolution of the state variables associated with the nodes on a graph. The states are associated with physical attributes of agents, e.g., the speed and/or location of vehicles. Efficient coordination then corresponds to the optimization of dynamics (how fast do vehicles travel) that may be subject to constraints (travel must be collision-free). The aim of this paper is (i) the formulation of learnable constrained dynamics which governs the transition of states under constraints over a graph and (ii) to show its industrial application. Firstly, we formulate continuous ordinary differential equations (ODEs), namely forward propagation of state transitions over a graph and backward propagation to optimize model parameters for the learnable constrained dynamics. Discretization of these continuous ODEs results in the neural architecture CoordiNet. Secondly, as an application of CoordiNet, we address a traffic coordination problem by learning constrained dynamics such that vehicles can travel as fast as possible without collisions. Simulation experiments of traffic coordination confirm that our method maximizes the vehicles' speed states while avoiding collisions.

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

http://hdl.handle.net/10453/177697