Show simple item record

dc.contributor.authorBerthling-Hansen, Gabriel
dc.contributor.authorMorch, Eivind
dc.contributor.authorLøvlid, Rikke Amilde
dc.contributor.authorGundersen, Odd Erik
dc.date.accessioned2020-03-09T09:41:09Z
dc.date.available2020-03-09T09:41:09Z
dc.date.created2018-11-30T17:33:26Z
dc.date.issued2018
dc.identifier.isbn978-1-5386-5288-6
dc.identifier.urihttp://hdl.handle.net/11250/2645958
dc.description.abstractComputer generated forces are simulated units that are used in simulation based training and decision support in the military. These simulations are used to help trainees build a mental model of how different scenarios could play out, and thus give them a better situation awareness when conducting operations in real life. The behaviour of these simulated units should be as realistic as possible, so that the lessons learned while simulating are applicable in real situations. However, it is time consuming and difficult to build behaviour models manually. Instead, we explore the possibility of applying machine learning to generate behaviour models from a set of examples. In this paper we present the results of our preliminary experiments on using machine learning for behaviour modelling. We implement a follow behaviour by using behaviour trees that are evolved using genetic algorithms. The fitness of the evolved behaviour trees have been evaluated by comparing them with a manually generated behaviour tree that implements the behaviour properly. The genetic algorithm converges to a tree that is very similar to the manually generated behaviour tree, suggesting that the method works. Further work is necessary to test whether this approach will work on more complex behaviours.nb_NO
dc.language.isoengnb_NO
dc.publisherIEEEnb_NO
dc.relation.ispartofProceedings of 2018 IEEE International Conference on Cognitive and Computational Aspects of Situation Management
dc.titleAutomating Behaviour Tree Generation for Simulating Troop Movementsnb_NO
dc.typeChapternb_NO
dc.description.versionacceptedVersionnb_NO
dc.source.pagenumber147-153nb_NO
dc.identifier.doihttp://dx.doi.org/10.1109/COGSIMA.2018.8423978
dc.identifier.cristin1637799
dc.description.localcode© 2018 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.nb_NO
cristin.unitcode194,63,10,0
cristin.unitnameInstitutt for datateknologi og informatikk
cristin.ispublishedtrue
cristin.fulltextpostprint
cristin.qualitycode1


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record