Developing an Artificial Intelligence Engine

Michael van Lent and John Laird. Developing an Artificial Intelligence Engine

Book: Artificial Intelligence for Games

Ian Millington and John Funge. Artificial Intelligence for Games (2009). Morgan Kaufmann.

Game: Neuro-Evolving Robotic Operatives

Game: Xpilot-AI Genetic Algorithm

Paper: The Painful Face – Pain Expression Recognition Using Active Appearance Models

Ahmed Bilal Ashraf, Simon Lucey, Jeffrey F. Cohn, Tsuhan Chen, Zara Ambadar, Kenneth M. Prkachin, and Patricia E. Solomon. 2009. The painful face - Pain expression recognition using active appearance models. Image Vision Comput. 27, 12 (November 2009), 1788-1796.

Self-reported pain is a big problem because it is difficult to interpret and may be impaired or not even possible, as in young children or the severely ill. The authors of this paper tackle this problem by developing a computer vision system that automatically recognizes acute pain.

To achieve their goal, adult patients with rotator cuff injury were video-recorded while a physiotherapist manipulated their affected and unaffected shoulder. From these ratings, sequences were categorized as no-pain (rating of 0), pain (rating of 3, 4, or 5), and indeterminate (rating of 1 or 2). And a facial expresion detector were implemented, as can be seen in the figure below.

Paper: Human-Level AI's Killer Application: Interactive Computer Games

John E. Laird and Michael van Lent. 2000. Human-Level AI's Killer Application: Interactive Computer Games. In Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence. AAAI Press 1171-1178.

What I most like about this article was the review of the major genres of video games which human-level AI is relevant and all the discussion of how AI could improve these games, and how these games provide research problems for AI.

All this information is collected together in the figure below. 

Paper: A Survey on the Need and Use of AI in Game Agents

Sule Yildirim and Sindre Berg Stene. 2008. A survey on the need and use of AI in game agents. In Proceedings of the 2008 Spring simulation multiconference (SpringSim '08). Society for Computer Simulation International, San Diego, CA, USA, 124-131.

This paper is a good survey on the use of various AI methodologies in commercial video games. They found that the most commonly used AI methodologies to achieve game AI can be stated as follows:

* Decision trees: can be realized by If-Then statements..

* Fine state machines

* Command hierarchies

* Manager task assignment

* Path finding (A*)

* Terrain analysis

* Influence mapping

* Formations

* Flocking

* Emergent behaviour

* Artificial Neural Networks 

* Genetic Algorithms

* Fuzzy logic

One of the most interesting AI approches listed above is emergrnt behavior. This kind of AI has been explored in Black & White.

Also, they present a misture of needed AI depending of the type of game. For example, In RPG games, a team is built up to reach a common goal. The intelligence required from a team or from individual characters depends on how complex it is to reach to the common goal.

Game: Armored Core: Verdict Day

Armored Core, From Software, is a mech fighting war series. The new big feature for Verdict Day is the UNAC system. Like Armored Core V, Verdict Day is about building teams of Core fighters and letting the game’s three warring factions duel it out. Each playthrough is a season, with Red, Blue, and Green teams fighting in skirmishes around the world until only one controls everything. The problem in V according to the producer, is that there weren’t enough people playing the actual game for people to form teams. The UNAC system is meant to be the remedy. Rather than forming a team of fighters with other actual players, you build an AI team.

Full article:
Armored Core: Verdict Day

Paper: Enemy NPC Design Patterns in Shooter Games

Gabriel Rivera, Kenneth Hullett, Jim Whitehead. Enemy NPC Design Patterns in Shooter Games (2012). Proceedings of the 1st Workshop on Design Patterns in Games.

This paper presents design patterns for NPCs in shooter games and explores their effects on gameplay.


Elements of an NPC
- Movement Type:
     * Flanking Intensive
     * Passive
     * Slow Push
     * Rush
     * Cautious
- Movement Range - This is how far the NPC will move during an engagement. This can be Low, Medium, or High.
- Movement Frequency - This is how often the NPC will change their position during an engagement. This can be Low, Medium,
or High.
- Attack Frequency – This describes how often the NPC will initiate an attack. This can be Low, Medium, or High.
- Weapon Type:
     * Sniping Weapon
     * Close Blast
     * Assault
     * Weapon Projectile
     * Power Weapon
     * Melee Weapon
- Weapon Damage – A general indicator on how much damage the NPC will do to the player’s Health, Shields, or Armor. This can
be Low, Medium, or High.
- Armor/Health – This denotes how much damage the NPC can take before being killed. This will typically be linked to how hard
the NPC is to defeat. This can be Low, Medium, or High.
- Motive:
     * Challenge – The degree of difficulty within a combat encounter.
     * Tension – The degree of mental stress the player experiences during a combat encounter.
     * Pacing – The degree of movement that the player will engage in during a combat encounter.

Structure Patterns of NPC Design
     Name - The name of the pattern should describe what the pattern does essentially.
     Description - A brief description of how the pattern is typically used and the effect it has on gameplay. This can be seen as the primary role of the enemy NPC.
     Affordances – This section lists the elements of the NPC and what those elements can be broken down into.
     NPC Relationships – Description of any special relationships with other patterns. This includes an Enemy NPC switching to a different pattern.
     Examples - Some examples from well-known games

Example: How one hospital is using video games to manage kids' pain

http://www.denverpost.com/digitalfirstmedia/ci_22951996/how-one-hospital-is-using-video-games-manage

Thesis: Jonathan

Future Work

Multi-Agent System
- Extend the system to support multiple teams at the same time.
- Allow the system to dynamically change learning and/or prediction agents.
- Implement dynamic unit grouping and Captain creation to allow easy scaling of total units controlled at the same time.

Learning AI
- Implement a prediction AI that can work together with the imitative one in order to create varying and interesting gameplay decisions.
- Extend the system to incorporate co-operative game styles.
- Use a multi neural network approach to allow strategy adaptation and dynamic difficulty adjustment.
- Add a dynamic factory creation/destruction factor to the learning al- gorithm.

Thesis: Pedestrian Simulations with the Social Force Model

Anders Johansson, Kristian Lindgren, and Dirk Helbing. Pedestrian Simulations with the Social Force Model (2004). Dresden University of Technology, Germany.

For this thesis, they implement different simulations using the Social Force Model (Helbing, 1991, 1995, 1997; Helbing and Moln ́ar, 1995; Helbing and Vicsek, 1999; Helbing et al., 2000; Moln ́ar, 1996a, 1996b). Model is discussed, which is suitable for both small-scale pedestrian simulations as well as computation- ally fast large-scale pedestrian simulations.

The model itself consist of some primitives:

- Agent: A pedestrian with a set of properties.

- Obstacle: A wall that will produce forces onto agents in the vicinity.

- ForceF ield: A polygon area with a constant force within. Can be used to model stairs or sloping floors.

- Goal: A location where agents want to go.

The pedestrian movement is built up by different forces:

- Obstacle forces: Repulsive forces are applied to all pedestrians in the vicinity of the obstacle with an increasing magnitude when the distance is decreasing.

- Pedestrian forces: Between all pedestrians there are repulsive forces that increase in magnitude when the distance is decreasing.

Among the applications one can find:

- evacuation of soccer arenas and theaters.

- self-organization phenomena such as lane formation, stripe formation.

Paper: How simple rules determine pedestrian behavior and crowd disasters

Mehdi Moussaïd, Dirk Helbing, and Guy Theraulaz. How simple rules determine pedestrian behavior and crowd disasters (2011). Social Sciences - Psychological and Cognitive Sciences - Physical Sciences - Applied Physical Sciences: NAS 2011 108 (17) 6884-6888; published ahead of print April 18, 2011, doi:10.1073/pnas.1016507

In this paper, a cognitive science approach is proposed, which is based on behavioral heuristics. The authors suggest that, guided by visual information, namely the distance of obstructions in candidate lines of sight, pedestrians apply two simple cognitive procedures to adapt their walking speeds and directions.

Their model predicts the emergence of self-organization phenomena, such as the spontaneous formation of unidirectional lanes or stop-and-go waves.

Example: Battle Zone

This game is widely considered to be the first computer-based serious game. 

Everything in this arcade is rendered in full 3-D graphics with vectors graphics. It was endorsed and used by the US military while some atari staff members refused to work on the project because of this. 

Paper: Expressive AI: Games and Artificial Intelligence

Michael Mateas. Expressive AI: Games and Artificial Intelligence (2003). Proceedings of International DiGRA Conference.

In this paper, Michael argues that game AI should be considered as an interdisciplinary agenda linking games studies, design practice, and technical research. The author call this new interdisciplinary agenda expressive AI.

A good example is how Space Invaders enemies behave. They move purely mechanically and appear to shoot randomly – they don’t require a psychological read (goals, emotions, and so forth) in order to make sense of them. From this perspective, the enemy ships in Space Invaders are really part of the physics of the game, not AI. Game AI lies at the intersection of player perception (the player is able to read part of the game behavior as alive) and the game code that supports this perception.

Example: PlayMancer

PlayMancer is a platform for rapid development of serious games, with a special focus on therapeutic support games for behavioral and addictive disorders. It is modular and combines techniques from multimodal interaction (speech, touch, biosensors and motion-tracking), 3D engines, virtual and augmented reality, speech recognition and natural language processing.

http://youtu.be/8AS4p_YYxMk
http://youtu.be/SPSFDvVYa_s

Paper: State of the Art Report on Serious games: Blurring the lines between recreation and reality

Eirik Vik. State of the Art Report on Serious games: Blurring the lines between recreation and reality. 2009. INF358 Seminar in Visualization, The Eurographics Association.


This paper provides a general overview of Serious Games. What I liked more of this paper was:

Serious Game taxonomy
Eirik Vik propose three different ways to classify Serious Games:

- Approach in terms of play:
     * Based Some: There are clear goals to reach.
     * Play-based: There are not defined goals. There is no real sense of winning or losing.

- Approach in terms of game play:
     * Turn-based
     * Real-time: The real-time option is by far the more realistic of the two.

- Via what domain it is intended for:
     * Health care
     * Defense
     * Education
     * Management
     * Government

Paper: Serious Games for Rehabilitation A Survey and a Classification Towards a Taxonomy

Rego, P.; Moreira, P.M.; Reis, L.P., "Serious games for rehabilitation: A survey and a classification towards a taxonomy," Information Systems and Technologies (CISTI), 2010 5th Iberian Conference on , vol., no., pp.1,6, 16-19 June 2010


This paper presents fundamental concepts relating to Serious Games followed by a survey of relevant work and applications on Serious Games for Rehabilitation.

As a reference, they  adopted the RehaCom System (see example link). This is a serious game application widely used for cognitive rehabilitation and well grounded in neuro-scientific theory.

Based on the literature reviewed they identify as important main criteria for the classification of Serious games in the rehabilitation area the following ones:

     * Application area
     * Interaction Technology
     * Game interface
     * Number of players
     * Adaptability
     * Performance Feedback
     * Progress monitoring
     * Game portability


Next table displays the classification.

Example:
http://anatomicalconcepts.com/index.php/products/gloreha-hand-rehabilitation#

Paper: Motivation based difficulty adaptation for therapeutic games

Hocine, N.; Gouaich, A.; Di Loreto, I.; Joab, M., "Motivation based difficulty adaptation for therapeutic games," Serious Games and Applications for Health (SeGAH), 2011 IEEE 1st International Conference on , vol., no., pp.1,8, 16-18 Nov. 2011

This paper presents presents a difficulty adaptation technique dedicated to a family of therapeutic games for post-stroke rehabilitation based on therapeutic serious game, they focus in upper limb rehabilitation.

As introduction they talk about studies that suggest intensive training (many repetitions) while giving feedbacks and motivating the patients can have an important impact on the patients’ skills recover.  And a person who enjoys what he is doing spends more time developing his skills in a given activity.

They developed a game that is based on the Wii-balance from Nintendo. This game aims to improve player’s equilibrium capabilities while achieving the game goals.

Paper: Understanding the Power of Augmented Reality for Learning

Gail Carmichael, Robert Biddle, David Mould. Understanding the Power of Augmented Reality for Learning (2012). World Conference on E-Learning in Corporate, Government, Healthcare, and Higher Education. Conference Paper

This paper provides a theoretical grounding that explains the underlying value of AR for learning and identify when it is a suitable interface. Also, they define four main categories of advantages of AR:

Reality for Free
* Content

* Behavior

* Multiple Senses

Virtual Flexibility
* Customization
* Impossibility

Invisible Interface
* Natural movement

* Single focus

Spatial Awareness
* Adjust to surroundings
* Align spatially

These advantages can be used to decide whether augmented reality is a good interface for a particular type of learning scenario.

Design Questions
The more questions a designer can answer yes to here, the stronger the case for using AR becomes.
 * Is there a real-world environment that the application or associated task is or should be set in?
 * Is there a strong, non-arbitrary association between the virtual data and objects your application uses and some aspect of the environment?
 * Is it important that details of the environment, from content to behavior, be preserved?
 * If the application supports learning a specific task, is this a non-abstract task that is already performed in the real world?
 * Does the application benefit from real-world context?

Paper: Augmented Reality Games for Upper-Limb Stroke Rehabilitation

Burke, J. W.; McNeill, M. D J; Charles, D.K.; Morrow, P.J.; Crosbie, J.H.; McDonough, S.M., "Augmented Reality Games for Upper-Limb Stroke Rehabilitation," Games and Virtual Worlds for Serious Applications (VS-GAMES), 2010 Second International Conference on , vol., no., pp.75,78, 25-26 March 2010

In this paper they present some serious games that use augmented reality for upper limb stroke rehabilitation.

Demos:

- It is interesting how they adapt the game depending on the initial calibration results.

- I like the idea of the game but not the AR markers they have to use.
- I don't like that this AR game doesn't adapt to the environment

They  identified three aspects of game design which are important for the user experience in a rehabilitation game:
* meaningful play
* challenge
* conservative handling of failure

Paper: Player Modeling for Intelligent Difficulty Adjustment

Olana Missura and Thomas. 2009. Player Modeling for Intelligent Difficulty Adjustment. In Proceedings of the 12th International Conference on Discovery Science (DS '09).

In the other articles I read this week I focused on the interface design. I like this article because is very important to provide players the appropriate and increasing difficulty. Wrong choices can easily lead to players stopping to play the game as they get bored or frustrated.

Paper: Pervasive Games: Bringing Computer Entertainment Back to the Real World

Carsten Magerkurth, Adrian David Cheok, Regan L. Mandryk, and Trond Nilsen. 2005. Pervasive games: bringing computer entertainment back to the real world. Comput. Entertain. 3, 3 (July 2005), 4-4.


Este artículo me gustó porque es una buena introducción a los Pervasive Games. En este género, juegos tradicionales o real-world games son aumentados con la ayuda de computadoras. Otra forma de verlos es como si videojuegos puramente virtuales son traídos al mundo real.

Algunos de los subgéneros de los pervasive games son: smart toys, affective games, tabletop games, location-aware games, y augmented reality games. De estos subgéneros, los que más me llamaron la atención son los Augmented Tabletop Games. Y lo que más me atrae de estos juegos es su componente social, que pueden ser jugados por varias personas a la vez, y de no tener el hardware necesario, pueden jugarse con interfaces tradicionales como un ratón y teclado.

A continuación anexo una imagen de un ejemplo de Augmented Tabletop Games. 

Paper: A Case Study of Augmented Reality Serious Games

A Case Study of Augmented Reality Serious Games by Fotis Liarokapis, Sara De Freitas.

Este artículo se centra en examinar los problemas que involucra el diseñar e implementar un serious game que haga uso de ambientes de Realidad Aumentada (AR). Sobre este tema, proponen que todo framework para diseñar videojuegos serios en ambientes AR, deben de considerar las siguientes 4 dimensiones:

También da varios ejemplos de aplicaciones, pero se centra en dos: ARPuzzle y ARBreakout.

Para conocer cómo recibían estos juegos los alumnos de la escuela, fue que comenzaron con un programa piloto con 60 estudiantes. Las partes a evaluar los juegos fueron: visualización, colaboración y aprendizaje. En general les fue bien a los dos juegos en todos los apartados excepto la visualización.

Liga al paper:
http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.158.7434&rep=rep1&type=pdf