A Control-Theoretic Approach to Adaptive Physiological Games

Avinash Parnandi, Youngpyo Son, Ricardo Gutierrez-Osuna
2013 2013 Humaine Association Conference on Affective Computing and Intelligent Interaction  
This paper presents an adaptive biofeedback videogame that aims to maintain the player's arousal level at an optimum level by monitoring physiological signals and manipulating game difficulty accordingly. We use concepts from classical control theory to model the interaction between human physiology and game difficulty during game play. Based on this control model, we have developed a real-time car-racing game with adaptive game mechanics. Specifically, we utilized car speed, road visibility,
more » ... d steering jitter as three mechanisms to manipulate game difficulty. We propose quantitative measures to characterize the extent to which these three game adaptations can manipulate the player's arousal. For this purpose, we used electrodermal activity (EDA) as a physiological correlate of arousal. We have validated our approach by conducting experimental trials with 20 subjects in both open-loop (no feedback) and closed-loop (negative feedback) conditions. Our results show statistically significant differences among the three game mechanics in terms of their effectiveness. Specifically, manipulating car speed provides higher arousal levels than modulating road visibility or vehicle steering. Finally, we discuss the theoretical and practical implications of our approach.
doi:10.1109/acii.2013.8 dblp:conf/acii/ParnandiSG13 fatcat:4fez75e5bff5xaygh54hiz4t5e