Multi-Horizon Multi-Agent Planning Using Decentralised Monte Carlo Tree Search

Seiler, KM; Kong, FH; Fitch, R

Multi-Horizon Multi-Agent Planning Using Decentralised Monte Carlo Tree Search

Seiler, KM Kong, FH Fitch, R

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Robotics and Automation Letters, 2024, 9, (9), pp. 7715-7722
Issue Date:: 2024-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

The embargo period expires on 10 Jul 2026

Adobe PDF

Download Accepted versionAdobe PDF (436.05 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Seiler, KM
dc.contributor.author	Kong, FH
dc.contributor.author	Fitch, R https://orcid.org/0000-0003-2215-5188
dc.date.accessioned	2024-09-05T09:33:47Z
dc.date.available	2024-09-05T09:33:47Z
dc.date.issued	2024-01-01
dc.identifier.citation	IEEE Robotics and Automation Letters, 2024, 9, (9), pp. 7715-7722
dc.identifier.issn	2377-3766
dc.identifier.issn	2377-3766
dc.identifier.uri	http://hdl.handle.net/10453/180651
dc.description.abstract	We propose multi-horizon Monte Carlo tree search (MH-MCTS), the first framework for integrated hierarchical multi-horizon, multi-agent planning based on Monte Carlo tree search (MCTS). The method employs multiple simultaneous MCTS optimisations for each planning level within each agent, which are designed to optimise a joint objective function. Using concepts from decentralised Monte Carlo tree search (Dec-MCTS), the individual optimisations continuously exchange information about their current plans. This breaks the common top-down only information flow within the planning hierarchy and allows higher level optimisers to consider progress made by lower level planners. The method is implemented for survey missions using a fleet of ground robots. Simulation results with different mission profiles show substantial performance improvements of the new method of up to 59% compared to traditional MCTS and Dec-MCTS.
dc.language	English
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartof	IEEE Robotics and Automation Letters
dc.relation.isbasedon	10.1109/LRA.2024.3426273
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.subject	0913 Mechanical Engineering
dc.subject.classification	4007 Control engineering, mechatronics and robotics
dc.subject.classification	4602 Artificial intelligence
dc.title	Multi-Horizon Multi-Agent Planning Using Decentralised Monte Carlo Tree Search
dc.type	Journal Article
utslib.citation.volume	9
utslib.for	0913 Mechanical Engineering
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/Strength - RI - Robotics Institute
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Mechanical and Mechatronic Engineering
pubs.organisational-group	University of Technology Sydney/All Manual Groups
pubs.organisational-group	University of Technology Sydney/All Manual Groups/Robotics Institute (RI)
pubs.organisational-group	University of Technology Sydney/All Manual Groups/Centre for Advanced Manufacturing (CAM)
pubs.organisational-group	University of Technology Sydney/All Manual Groups/Centre for Advanced Manufacturing (CAM)/Associate Member
utslib.copyright.status	open_access	*
utslib.copyright.embargo	2026-07-10T00:00:00+1000Z
dc.date.updated	2024-09-05T09:33:45Z
pubs.issue	9
pubs.publication-status	Published
pubs.volume	9
utslib.citation.issue	9

Abstract:

We propose multi-horizon Monte Carlo tree search (MH-MCTS), the first framework for integrated hierarchical multi-horizon, multi-agent planning based on Monte Carlo tree search (MCTS). The method employs multiple simultaneous MCTS optimisations for each planning level within each agent, which are designed to optimise a joint objective function. Using concepts from decentralised Monte Carlo tree search (Dec-MCTS), the individual optimisations continuously exchange information about their current plans. This breaks the common top-down only information flow within the planning hierarchy and allows higher level optimisers to consider progress made by lower level planners. The method is implemented for survey missions using a fleet of ground robots. Simulation results with different mission profiles show substantial performance improvements of the new method of up to 59% compared to traditional MCTS and Dec-MCTS.

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

http://hdl.handle.net/10453/180651