Conference Paper

Towards Automatic Personalized Content Generation for Platform Games.

Conference: Proceedings of the Sixth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010, October 11-13, 2010, Stanford, California, USA
Source: DBLP
0 Followers
 · 
80 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: The recent outbreak of indie games has popularized volumetric terrains to a new level, although video games have used them for decades. These terrains contain geological data, such as materials or cave systems. To improve the exploration experience and due to the large amount of data needed to construct volumetric terrains, industry uses procedural methods to generate them. However, they use their own methods, which are focused on their specific problem domains, lacking customization features. Besides, the evaluation of the procedural terrain generators remains an open issue in this field since no standard metrics have been established yet. In this paper, we propose a new approach to procedural volumetric terrains. It generates completely customizable volumetric terrains with layered materials and other features (e.g., mineral veins, underground caves, material mixtures and underground material flow). The method allows the designer to specify the characteristics of the terrain using intuitive parameters. Additionally, it uses a specific representation for the terrain based on stacked material structures, reducing memory requirements. To overcome the problem in the evaluation of the generators, we propose a new set of metrics for the generated content.
    The Visual Computer 09/2013; 30(9):997-1007. DOI:10.1007/s00371-013-0909-y · 1.07 Impact Factor
  • Source
    03/2015; Springer., ISBN: 978-3-319-16497-7
  • [Show abstract] [Hide abstract]
    ABSTRACT: Current approaches to game design improvements rely on gameplay testing, an iterative process following the test, try and fix pattern, relying on target audience feedback via standard questionnaires. Besides being a very time consuming phase, it is also highly subjective. In this paper, we demonstrate a generalizable approach for building predictive models of players' affective reactions across games and genres. Our aim is two-fold: 1) That game developers can use these models to more easily and accurately tune game parameters, allowing improved gaming experiences, and 2) That these models can be used as the basis for parameterisable and adaptive affective gaming. This paper describes our preliminary results regarding a novel, physiological-based method for emotional player profiling, which consists on the following three phases: (i) monitoring players' emotional states and game events, (ii) identifying player's emotional reactions to game events and (iii) individual and cluster-based modelling of players emotional reactions.
    2014 9th Iberian Conference on Information Systems and Technologies (CISTI); 06/2014