Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Affective Decision Making in Artificial Intelligence: Making Virtual Characters With High Believability
Linköping University, Department of Science and Technology, Media and Information Technology. Linköping University, The Institute of Technology.
2012 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Artificial intelligence is often used when creating believable virtual characters in games or in other types of virtual environments. The intelligent behavior these characters show to the player is often flawed, leading to a worse gameplay experience. In particular, there is often little or no emotional impact on the decision making of the characters. This thesis focuses on extending decision-making and pathfinding mechanisms for virtual characters, with a particular focus on the use of emotions. The thesis is divided into three parts.

The first part is an introductory study concerning the requirements designing a believable virtual character places on the architecture used. Gameplay design patterns are used as a tool to analyze the proposed agent architecture and discussions are presented regarding the necessary properties of such an architecture with respect to gameplay.

The second part extends two action selection mechanisms to include emotional impact. In particular, behavior networks are extended to take complex emotional impact into account, including emotional parameters, emotional goals, and emotional influences.Moreover, time-discounting is introduced into behavior networks as a factor in the decision making. The time-discounting is also under emotional influence. The second action selection mechanism extended to use emotional impact is behavior trees. Since behavior trees are widely used by game designers, allowing full control over the characters’ behaviors, the work in this thesis proposes a new type of emotional selector which only affects a part ofthe behavior tree, leaving the control in the hands of the designer.

The third part focuses on more complex pathfinding where more factors than finding the shortest collisionfree path through an environment are considered. A new type of visibility map is introduced. Using the knowledge of the virtual character about previous enemy positions, a more accurate visibility map is created. The visibility map is used for covert pathfinding, where the character tries to find a path through an environment while trying to minimize the risk of being seen by the enemy. Finally, a new kind of pathfinding, emotional pathfinding, is introduced, based on the use of emotion maps. Humans often have emotional attachment to geographical locations because they have previously felt emotions at those locations. This approach takes advantage of this knowledge and enables a virtual character to find a path through an environment that is as emotionally pleasant as possible.

Place, publisher, year, edition, pages
Linköping: Linköping University Electronic Press, 2012. , 85 p.
Series
Linköping Studies in Science and Technology. Dissertations, ISSN 0345-7524 ; 1477
Keyword [en]
Artificial intelligence, emotions, decision making, pathfinding
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:liu:diva-84700ISBN: 978-91-7519-792-0 (print)OAI: oai:DiVA.org:liu-84700DiVA: diva2:561201
Public defence
2012-11-09, K3, Kåkenhus, Campus Norrköping, Linköpings universitet, Norrköping, 09:30 (English)
Opponent
Supervisors
Available from: 2012-10-17 Created: 2012-10-17 Last updated: 2013-09-12Bibliographically approved
List of papers
1. Affective States in Behavior Networks
Open this publication in new window or tab >>Affective States in Behavior Networks
2009 (English)In: Intelligent Computer Graphics / [ed] Dimitri Plemenos, Springer , 2009, 1, Vol. 240, 19-39 p.Chapter in book (Other academic)
Abstract [en]

Several studies within the field of neuroscience, psychology and economics have concluded that emotions are vital for the human decision making process. Without emotions, humans cannot make reasonable choices, a fact that has until recently been neglected within the area of action selection. We propose a method to extend behavior networks to include affective impact. The work by Loewenstein et al. will be our main motivation. In our model the parameters of the behavior network change dynamically according to the agents emotional state and the goals of the network are entirely emotional. The agents risk judgement also changes depending on its current emotions. The aim is to create a platform for modeling human-like affective decision making. Our goal is to create natural and interesting non-player characters for games or game-like applications.

Place, publisher, year, edition, pages
Springer, 2009 Edition: 1
Series
Studies in Computational Intelligence, ISSN 1860-949X ; Vol. 240
Keyword
virtual agents, decision making, emotions, behavior networks
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-53444 (URN)10.1007/978-3-642-03452-7_2 (DOI)000273182900002 ()978-3-642-03451-0 (ISBN)978-3-642-03452-7 (ISBN)
Available from: 2010-01-22 Created: 2010-01-22 Last updated: 2014-09-08Bibliographically approved
2. Introducing Time in Emotional Behavior Networks
Open this publication in new window or tab >>Introducing Time in Emotional Behavior Networks
2010 (English)In: IEEE Symposium on Computational Intelligence and Games (CIG), 2010, IEEE , 2010, 297-304 p.Conference paper, Published paper (Refereed)
Abstract [en]

In realistic scenarios an agent should not assume that the effects of its action are immediate. However, behavior networks have not previously been designed to model this, but rather have assumed that all effects are immediate. In this paper we introduce effect delay time and time-discounting into the decision making module of our agent architecture. We describe the previous emotional behavior network, introduce the concept of effect delay and let emotions influence how much time-discounting should be made to the delay time. Finally, we demonstrate the strength of our model by simulating two decision making problems.

Place, publisher, year, edition, pages
IEEE, 2010
Keyword
behavior networks, time-discounting, artificial intelligence, emotions
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-62772 (URN)10.1109/ITW.2010.5593342 (DOI)978-1-4244-6297-1 (ISBN)978-1-4244-6296-4 (ISBN)
Conference
IEEE Conference on Computational Intelligence and Games, Dublin, August, 18-21
Available from: 2010-12-03 Created: 2010-12-03 Last updated: 2012-10-17Bibliographically approved
3. Knowledge-Based Probability Maps for Covert Pathfinding
Open this publication in new window or tab >>Knowledge-Based Probability Maps for Covert Pathfinding
2010 (English)In: Motion in Games / [ed] Ronan Boulic, Yiorgos Chrysanthou, and Taku Komura, Springer , 2010, 339-350 p.Chapter in book (Refereed)
Abstract [en]

Virtual characters in computer games sometimes need to find a path from point A to point B while minimizing the risk of being spotted by an enemy. Visibility calculations of the environment are needed to accomplish this. While previous methods have focused on either general visibility calculations or calculations based only on current enemy positions, we suggest a method to incorporate the agent’s knowledge of previous enemy positions. By creating a probability distribution of the positions of the enemies and using this in the visibility calculation, we create a more accurate visibility map.

Place, publisher, year, edition, pages
Springer, 2010
Series
Lecture Notes in Computer Science, ISSN 0302-9743 (print), 1611-3349 (online) ; 6459
Keyword
artificial intelligence, pathfinding, visibility, covert
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-62771 (URN)10.1007/978-3-642-16958-8_32 (DOI)978-3-642-16957-1 (ISBN)978-3-642-16958-8 (ISBN)
Conference
Motion in Games Third International Conference, MIG 2010, Utrecht, The Netherlands, November 14-16, 2010.
Available from: 2010-12-03 Created: 2010-12-03 Last updated: 2014-09-17Bibliographically approved
4. AI Design for Believable Characters via Gameplay Design Patterns
Open this publication in new window or tab >>AI Design for Believable Characters via Gameplay Design Patterns
Show others...
2011 (English)In: Business, Technological and Social Dimensions of Computer Games: multidisciplinary developments / [ed] Maria Manuela Cruz-Cunha, Vitor Hugo Carvalho, Paula Cristina Almeida Tavares, IGI Global , 2011, 15-31 p.Chapter in book (Other academic)
Abstract [en]

We address the problem of creating human-like, believable behavior for game characters. To achieve character believability in games, the game designer needs to develop that character so that it fulfills as many aspects of believability as possible. With believable behavior we mean that the game is consistently structured in terms of narration or gameplay so that it is possible to build and maintain coherent relations between the actions of the characters. In this paper, we first analyze the general patterns for game characters design in detail concentrating on the aspects that are relevant to the AI design. Then, we present an agent architecture that we are developing, and discuss how this architecture can address the identified design patterns.

Place, publisher, year, edition, pages
IGI Global, 2011
Keyword
Video games industry, Video games -- Design, Video games -- Social aspects
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-65785 (URN)10.4018/978-1-60960-567-4.ch002 (DOI)978-1-60960-567-4 (ISBN)1-60960-567-5 (ISBN)978-1-60960-568-1 (ISBN)
Available from: 2011-02-20 Created: 2011-02-20 Last updated: 2014-12-19Bibliographically approved
5. Pathfinding with Emotion Maps
Open this publication in new window or tab >>Pathfinding with Emotion Maps
2012 (English)In: Intelligent Computer Graphics 2011 / [ed] Dimitri Plemenos, Georgios Miaoulis, Springer, 2012, 139-155 p.Chapter in book (Refereed)
Abstract [en]

In Computer Graphics, the use of intelligent techniques started more recently than in other research areas. However, during these last two decades, the use of intelligent Computer Graphics techniques is growing up year after year and more and more interesting techniques are presented in this area.The purpose of this volume is to present current work of the Intelligent Computer Graphics community, a community growing up year after year. This volume is a kind of continuation of the previously published Springer volumes “Artificial Intelligence Techniques for Computer Graphics” (2008), “Intelligent Computer Graphics 2009” (2009) and “Intelligent Computer Graphics 2010” (2010).This volume contains selected extended papers from the last 3IA Conference (3IA’2011), which has been held in Athens (Greece) in May 2011. This year papers are particularly exciting and concern areas like virtual reality, artificial life, data visualization, games, global illumination, point cloud modelling, declarative modelling, scene reconstruction and many other very important themes

Place, publisher, year, edition, pages
Springer, 2012
Series
Studies in Computational Intelligence, ISSN 1860-949X ; 374
Keyword
Engineering, Artificial intelligence, Computer graphics, Computational Intelligence, Artificial Intelligence
National Category
Computer and Information Science
Identifiers
urn:nbn:se:liu:diva-73059 (URN)10.1007/978-3-642-22907-7_8 (DOI)000301956000008 ()978-3-642-22906-0 (ISBN)978-3-642-22907-7 (ISBN)
Available from: 2011-12-14 Created: 2011-12-14 Last updated: 2014-11-26Bibliographically approved
6. Comparing Behavior Trees and EmotionalBehavior Networks for NPCs
Open this publication in new window or tab >>Comparing Behavior Trees and EmotionalBehavior Networks for NPCs
2012 (English)In: Intelligent Computer Graphics 2011, VIII / [ed] Dimitri Plemenos and Georgios Miaoulis, Springer, 2012, 139-155 p.Chapter in book (Refereed)
Abstract [en]

In Computer Graphics, the use of intelligent techniques started more recently than in other research areas. However, during these last two decades, the use of intelligent Computer Graphics techniques is growing up year after year and more and more interesting techniques are presented in this area.The purpose of this volume is to present current work of the Intelligent Computer Graphics community, a community growing up year after year. This volume is a kind of continuation of the previously published Springer volumes “Artificial Intelligence Techniques for Computer Graphics” (2008), “Intelligent Computer Graphics 2009” (2009) and “Intelligent Computer Graphics 2010” (2010).This volume contains selected extended papers from the last 3IA Conference (3IA’2011), which has been held in Athens (Greece) in May 2011. This year papers are particularly exciting and concern areas like virtual reality, artificial life, data visualization, games, global illumination, point cloud modelling, declarative modelling, scene reconstruction and many other very important themes

Place, publisher, year, edition, pages
Springer, 2012
Series
Studies in Computational Intelligence Volume, ISSN 1860-949X ; 374
Keyword
Engineering, Artificial intelligence, Computer graphics, Computational Intelligence, Artificial Intelligence
National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-84696 (URN)10.1007/978-3-642-22907-7_8 (DOI)000310619400041 ()978-3-642-22906-0 (ISBN)978-3-642-22907-7 (ISBN)
Available from: 2012-10-17 Created: 2012-10-17 Last updated: 2014-11-26Bibliographically approved
7. Emotions in Behavior Trees
Open this publication in new window or tab >>Emotions in Behavior Trees
(English)Manuscript (preprint) (Other academic)
Abstract [en]

Often the AI techniques for decision making used in commercial games are predictable and unadaptive. Arguably, this causes a lack of realism for the players. We believe that emotions are a vital part in the creation of interesting and believable non-player characters for games. In this paper, we present anextension to behavior trees that incorporates emotions into the decision making. Specifically, we introduce a new type of priority selector whose priorities are dynamically evaluated to allow for emotional influence. This selector takes into account timediscounting, risk perception, and planning as relevant factors of the decision making that emotions greatly influence. The objective of our work is to provide game developers with a technique tomodel gaming scenarios using emotional behavior trees.

National Category
Engineering and Technology
Identifiers
urn:nbn:se:liu:diva-84699 (URN)
Available from: 2012-10-17 Created: 2012-10-17 Last updated: 2012-10-17Bibliographically approved

Open Access in DiVA

Affective Decision Making in Artificial Intelligence: Making Virtual Characters With High Believability(5287 kB)4758 downloads
File information
File name FULLTEXT01.pdfFile size 5287 kBChecksum SHA-512
f3e9fb2e7303f96cf947883a33ae4b9feb69bf5fde8e8254d4ace52dfd87aa7bbc3c1257c54fba6dbc9989f0dc59414fbf7f148c1f618b480abb79fdda1bd35e
Type fulltextMimetype application/pdf
omslag(1212 kB)55 downloads
File information
File name COVER01.pdfFile size 1212 kBChecksum SHA-512
ce252866a6d758212ff5d0135e3268e5a7e46e28aa50666b23bc2651ea8065b4f42086bcd61228978e106435ee70c4ef584678e7e1e6059780d3cdf45883b74c
Type coverMimetype application/pdf

Search in DiVA

By author/editor
Johansson, Anja
By organisation
Media and Information TechnologyThe Institute of Technology
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar
Total: 4758 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 1480 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf