Visualization tool for gaming artificial intelligence

Real time strategy game is one of the hardest types of game a code for artificial intelligence. Thus, most of the artificial intelligence in commercial RTS games would be hard coded by scripting. There are a few problems in doing this. After implementation of the scripted AI in a RTS game, experts w...

Full description

Saved in:
Bibliographic Details
Main Author: Neo, Eric Jia Rong
Other Authors: Ong Yew Soon
Format: Final Year Project
Language:English
Published: 2012
Subjects:
Online Access:http://hdl.handle.net/10356/48836
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-48836
record_format dspace
spelling sg-ntu-dr.10356-488362023-03-03T20:40:56Z Visualization tool for gaming artificial intelligence Neo, Eric Jia Rong Ong Yew Soon School of Computer Engineering Centre for Computational Intelligence DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Real time strategy game is one of the hardest types of game a code for artificial intelligence. Thus, most of the artificial intelligence in commercial RTS games would be hard coded by scripting. There are a few problems in doing this. After implementation of the scripted AI in a RTS game, experts would still have to test and tweak the rules in the game. Also, after completion, the implementation could not be applied in other RTS games again which means scripting would have to be done from scratch again. Thus, lot of time is wasted in coding artificial intelligence in commercial RTS games. Thus, in this project, a system was developed in order to ensure artificial intelligence is coded easily. The system uses rule based intelligence as it is the easiest to implement and understand. For rule based intelligence, there are two components, knowledge base and inference engine. The knowledge base is handled by Rule Designer, a generic rule editor. This program is designed to require minimum typing, thus syntax mistakes would not happen as compared to coding it directly. Also, Rule Designer is designed such that any game could use this program to code their agents’ rule based intelligence. MemeWar, an Artificial Intelligence simulation project that is developed by the C2i lab, acts as the inference engine for this project. As it was not easy to test out artificial intelligence in the current system, a new mode called Sandbox Mode was created in order make testing artificial intelligence easier. Also, a new module called Power Up was created to give the agent more choices and make the game more complex. Thus, by using this system, it is now easier to code artificial intelligence for RTS games. Bachelor of Engineering (Computer Science) 2012-05-10T02:56:31Z 2012-05-10T02:56:31Z 2012 2012 Final Year Project (FYP) http://hdl.handle.net/10356/48836 en Nanyang Technological University 53 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
spellingShingle DRNTU::Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Neo, Eric Jia Rong
Visualization tool for gaming artificial intelligence
description Real time strategy game is one of the hardest types of game a code for artificial intelligence. Thus, most of the artificial intelligence in commercial RTS games would be hard coded by scripting. There are a few problems in doing this. After implementation of the scripted AI in a RTS game, experts would still have to test and tweak the rules in the game. Also, after completion, the implementation could not be applied in other RTS games again which means scripting would have to be done from scratch again. Thus, lot of time is wasted in coding artificial intelligence in commercial RTS games. Thus, in this project, a system was developed in order to ensure artificial intelligence is coded easily. The system uses rule based intelligence as it is the easiest to implement and understand. For rule based intelligence, there are two components, knowledge base and inference engine. The knowledge base is handled by Rule Designer, a generic rule editor. This program is designed to require minimum typing, thus syntax mistakes would not happen as compared to coding it directly. Also, Rule Designer is designed such that any game could use this program to code their agents’ rule based intelligence. MemeWar, an Artificial Intelligence simulation project that is developed by the C2i lab, acts as the inference engine for this project. As it was not easy to test out artificial intelligence in the current system, a new mode called Sandbox Mode was created in order make testing artificial intelligence easier. Also, a new module called Power Up was created to give the agent more choices and make the game more complex. Thus, by using this system, it is now easier to code artificial intelligence for RTS games.
author2 Ong Yew Soon
author_facet Ong Yew Soon
Neo, Eric Jia Rong
format Final Year Project
author Neo, Eric Jia Rong
author_sort Neo, Eric Jia Rong
title Visualization tool for gaming artificial intelligence
title_short Visualization tool for gaming artificial intelligence
title_full Visualization tool for gaming artificial intelligence
title_fullStr Visualization tool for gaming artificial intelligence
title_full_unstemmed Visualization tool for gaming artificial intelligence
title_sort visualization tool for gaming artificial intelligence
publishDate 2012
url http://hdl.handle.net/10356/48836
_version_ 1759856032423608320