Intelligent group movement and selection in realtime strategy games

Beume, Nicola; Danielsiek, Holger; Hein, Tobias; Naujoks, Boris; Piatkowski, Nico; Preuss, Mike; Stüer, Raphael; Thom, Andreas; Wessing, Simon

Intelligent group movement and selection in realtime strategy games

dc.contributor.author	Beume, Nicola	de
dc.contributor.author	Danielsiek, Holger	de
dc.contributor.author	Hein, Tobias	de
dc.contributor.author	Naujoks, Boris	de
dc.contributor.author	Piatkowski, Nico	de
dc.contributor.author	Preuss, Mike	de
dc.contributor.author	Stüer, Raphael	de
dc.contributor.author	Thom, Andreas	de
dc.contributor.author	Wessing, Simon	de
dc.date.accessioned	2009-05-12T16:02:17Z
dc.date.available	2009-05-12T16:02:17Z
dc.date.issued	2008-12	de
dc.description.abstract	Movement of groups in realtime strategy games is often a nuisance: Units travel and battle separately, resulting in huge losses and the AI looking dumb. This applies to computer as well as human commanded factions. We suggest to tackle that by using flocking improved by influence-map based pathfinding which leads to a much more natural and intelligent looking behavior. A similar problem occurs if the computer AI has to select groups to combat a specific target: Assignment of units to groups, especially for multiple enemy groups, is often suboptimal when units have very different attack skills. This can be cured by using offline prepared self-organizing feature maps that use all available information for looking up good matches. We demonstrate that these two approaches work well separately, but also that they go together very naturally, thereby leading to an improved and - via parametrization - very flexible group behavior. Opponent AI may be strenghtened that way as well as player-supportive AI. A thorough experimental analysis supports our claims.	en
dc.identifier.uri	http://hdl.handle.net/2003/26162
dc.identifier.uri	http://dx.doi.org/10.17877/DE290R-695
dc.language.iso	en	de
dc.relation.ispartofseries	Reihe CI; 255-08	de
dc.subject	evolutionary algorithms	en
dc.subject	neural networks	en
dc.subject	path finding	en
dc.subject	realtime strategy games	en
dc.subject	tactical decision making	en
dc.subject.ddc	004	de
dc.title	Intelligent group movement and selection in realtime strategy games	en
dc.type	Text	de
dc.type.publicationtype	report	de
dcterms.accessRights	open access

Files

Original bundle

Now showing 1 - 1 of 1

Name:: 25508.pdf
Size:: 410.53 KB
Format:: Adobe Portable Document Format
Description:: DNB

Download

Collections

Sonderforschungsbereich (SFB) 531