Difference between revisions of "Affective VideoGames"

Revision as of 10:43, 23 August 2010

Project description

The aim of this projects is to develop a software that can adapt a behaviour of an interactive videogame (a car game like TORCS or a similar parametrizable game) according to an evaluation of his/her emotional state. We will start by analizing biological signals to evaluate the emotional state. The goal is to maximize the engagement of the player, making her/him staying as long as possible in the "flow" state , by adapting the parameters of the videogame to her/his real emotional state.

The first part of the project consisted of the analysis of a set of VideoGames. In particular three different available open source games have been studied in order to receive feedbacks from the player (in terms of excitement), finding out which one is the most suitable for the goal of the project: the one potentially affecting most the player's emotions. The games that have been analyzed for this first stage of the project have been the following:

- a puzzle/action 3d game called Beaver Valley;

- TORCS (driving simulator);

- the music video game called Frets on Fire.

TORCS has been selected and experiments with it have been done in October 2009, leading to the definition of a methodology to face experiments and some preliminary results.

Here is an example of this experiment. The player is sitting in front of a desktop computer equipped with a keyboard. During the game the biological signal of the subject are acquired by sensors on the fingers and the ProComp Infiniti system.

• External link

Following this methodology, in March 2010 a new set of experiments have been performed with 80 volunteers. In these experiments, images from two cameras have also been recorded to allow the analysis of gestures and facial expressions. Luca Perego is working on these data and on biophysical data to establish relationships between the two.

From April 2010 Barbara Bruno and Antonella Belfatto are working on collecting new data and adapting the videogame behavior to the detected user preferences.

From May 2010 Giovanni Marco Zaccaria starts to work on the adapting the videogame behavior project. His specific role is to write a part of the opponents’s AI algorithms in C language so that they can receive a feedback from data-acquired biosignals processed. The result is to balance in real-time the game difficulty in order to make sure the human player’s enjoyment.

More details on the project are available under the discussion tab, accessible by involved airwiki users.

Students that worked on the project in the past

• Andrea Campana (Project work - Sep 2009)

• Andrea Tommaso Bonanno (MS Thesis - Dec 2009)

Laboratory work and risk analysis

Laboratory work for this project will be mainly performed at AIRLab/DEI. The only risks are related to the use of computers and data acquisition devices