Augmenting Artificial Intelligence Creativity: Event Segmentation and AI planning for Quest Generation

It appears your Web browser is not configured to display PDF files. Download adobe Acrobat or click here to download the PDF file.

Click here to download the PDF file.

Creator: 

Sanni, Mujahid Adegboyega

Date: 

2021

Abstract: 

The persistent rise in demand for content in the gaming industry means that programs with the ability to produce content autonomously will save an extraordinary amount of time and cost. In that context, this thesis proposes a novel architecture for procedural narrative generation and Implements it as software called Automatic Quest Planning Generator (AQPG). The architecture combines the computation of Event Segmentation Theory (EST) with Artificial Intelligence (AI) planning methods to automatically generate quests. The idea in this work is that since Event Segmentation generates actions and goals to facilitate planning in humans, a good representation of these types of events either in natural language text or other media should be able to automatically generate planning components for an AI planning system as well. Results from this work found that the AQPG system is capable of generating planning files that can be used for quest generation.

Subject: 

Artificial Intelligence
Psychology - Cognitive
Linguistics

Language: 

English

Publisher: 

Carleton University

Thesis Degree Name: 

Master of Cognitive Science: 
M.Cog.Sc

Thesis Degree Level: 

Master's

Thesis Degree Discipline: 

Cognitive Science

Parent Collection: 

Theses and Dissertations

Items in CURVE are protected by copyright, with all rights reserved, unless otherwise indicated. They are made available with permission from the author(s).