Applications of artificial potential fields for real time strategy games: Troop formations and movements used trained potential functions
This thesis describes the effort of adapting potential field methods towards man-
aging groups of units in real-time strategy game like environments. The focus is on
discovering the suitability for this technology to create realistic group behaviour
and whether it can be adapted to use learning for this purpose.
A flexible simulation system for units that are controlled by potential field
methods in environments similar to those found in real-time strategy games is
developed. This is then used to conduct experiments where different types of
group behaviour is sought after. Stochastic optimization techniques are applied
in an attempt to create and optimize desired group behaviour. The results are
discussed and future directions for this research are proposed.
Place, publisher, year, edition, pages
Institutt for datateknikk og informasjonsvitenskap , 2012. , 96 p.
ntnudaim:7580, MTDT datateknikk, Spillteknologi
IdentifiersURN: urn:nbn:no:ntnu:diva-19087Local ID: ntnudaim:7580OAI: oai:DiVA.org:ntnu-19087DiVA: diva2:566463
Langseth, Helge, ProfessorKofod-Petersen, Anders