Print Email Facebook Twitter Semantic navigation in video games Title Semantic navigation in video games Author Van Driel, L.M. Contributor Bidarra, A.R. (mentor) Faculty Electrical Engineering, Mathematics and Computer Science Date 2008-11-29 Abstract The exhibition of intelligent or challenging behavior by artificially controlled characters (AI) in computer games strongly depends on their navigational performance, often referred to as pathfinding. While recent games solve increasingly complex and specific navigation problems, the documented approaches to navigation remain primitive and isolated within the gaming software realm. We propose a semantic approach to navigation that allows AI to extract and incorporate a wide variety of navigation information into the planning of character behavior, including raw geometry, strategic objects, and abilities for locomotion. We design and implement a navigation system for Unreal Engine 3 that requires little designer intervention, has a rich interface for AI programmers, and can be extended with other types of semantic information. This subsystem proves to outperform the original navigation functionality by delivering more natural paths, fewer world annotation, and dynamic re-planning. Subject navigation To reference this document use: http://resolver.tudelft.nl/uuid:eca407ca-512c-4b17-82c2-dae9236a2066 Publisher TU Delft, Electrical Engineering, Mathematics and Computer Science, Media and Knowledge Engineering Part of collection Student theses Document type master thesis Rights (c) 2008 L.M. van Driel Files PDF ewi_vandriel_2008.pdf 1.4 MB Close viewer /islandora/object/uuid:eca407ca-512c-4b17-82c2-dae9236a2066/datastream/OBJ/view