Demos and Videos

From Center for Computer Games Research

Jump to: navigation, search


This page gathers some of the interactive demos and videos associated with the different projects running on the group as well as on-going on-line experiments.

Experiments

We are currently running two experiments to assess player experience in platform games and automatically generate levels that are tailored to each players needs. Play and help us collect as many data as possible

Experiment

CamOn - Lerpz Escape Experiment: this experiment is an evaluation of the impact of different types of camera control in computer games.

To participate just click on the image below and play! All you need is a Windows or Mac computer, a mouse and approximately 15 minutes of your time. Please note that this is an experimental project; therefore, be patient if any bug shows up. If you have any comment or suggestion, write me an email at pabu@itu.dk or leave a comment on this page.

Experiment page

Demos

Download and play three different java-based variants of a platform game. Let the game assess your emotional state using neuro models trained on 120 players and 327 players or play an adapted game that maximizes your frustration or level of fun.

Experience capture (120 p)
Experience capture (327p)
Affect-adaptive Mario Bross

This is the interactive preview of the CamOn library displayed at AIIDE in October 2009 based on the Island demo included in Unity 3d.

You can choose a shot type and see how the camera is animated in this dynamic environment; switch to Artificial Potential Field mode to visualize the field shape corresponding to each shot.

CamOn boder=1
Play in your browser Maze Ball, a prey/predator game used to investigate the impact of camera profiles on players' experience. Press 1 to 8 to view the different camera settings used in our experiments. MazeBall online boder=1

Videos

Towards Adaptive Serious Games for Conflict Resolution

We present an initial demonstrator towards the creation of an adaptive serious game for teaching conflict resolution. The game demonstrator is built around a simple resource management conflict scenario. The game monitors data about the behaviour and the cognitive focus of the player and generates content driven by the modelled player state automatically in order to guide her toward particular learning targets.

Camera Control

These videos present CamOn, an autonomous camera control system for real-time 3D applications. CamOn is a generalized camera control system able to produce well composed shots and smooth camera movements in dynamic environments.

Demo video of the CamOn capabilities to handle complex visual contraints like visibility in real-time.
On one hand this video shows how different camera configurations can change the information perceived by the player and on the other hand it shows how CamOn dynamically moves the camera to who or hide some scene subjects while the main character it's moving.
This demo shows the Ogre version of the library presented at AIIDE 09 in Stanford. The video shows an hypothetical stealth-game intro sequence; the scene includes several characters in a room, some steady and some moving.

Player Modeling in TRU

This is a project study focused on constructing models of players for the major commercial title Tomb Raider: Underworld (TRU). Emergent self-organizing maps are trained on high-level playing behavior data obtained from thousands of players that have played the TRU game

WiiHabilitation

The overall objective of the project is to investigate how game-based digital technology can be designed to install a stronger sense of continuity in the rehabilitation process as experienced by both the therapists and patients.

The video presents the four player types identified via self-organizing neural networks on data derived from thousands of Tomb Raider: Underworld players.
Procedural Content Generation within a slalom game for legs and hips rehabilitation.

Affective Camera Control in Games

The impact of virtual camera on players' psychophysiology is investigated in this project. These videos show MazeBall, a simple 3D prey/predator game used for these studies.

This video shows the game Maze Ball played with a fixed camera profile.
This video showcases the concept of adaptive camera control in games.

Dynamic Game Balancing

This project explores using the NEAT and rtNEAT neuro-evolution methodologies to generate intelligent opponents in real-time strategy (RTS) games. The main objective is to adapt the challenge generated by the game opponents to match the skill of a player in real-time, ultimately leading to a higher entertainment value perceived by a human player of the game.

Warrior producing NPC behavior in an RTS game.
Rapid winning NPC behavior in an RTS game using Neuro-Evolution (NEAT).

Capturing and Enhancing Player Entertainment in Games

This project pursues the design of user models that capture player satisfaction and the design of adaptive mechanisms that augment the value of those player satisfaction estimators.

Machine learning is used to capture the fun value of the player while playing. The game then adjusts itself (internal controls) to satisfy the needs of each player by increasing the predicted fun value. The videos show the adaptive Bug-Smasher game where adjustment of bug unpredictability and bug speed occur while play for maximizing the player's fun value.