Adaptive Motion Gaming AI for Health Promotion
This addresses health promotion in motion gaming users, but it is incremental as it applies existing methods (Monte-Carlo tree search) to a new domain.
The paper tackles the problem of promoting balanced use of body segments in full-body motion gaming by designing an AI that analyzes player health states and predicts how its actions will affect player movement and health, resulting in improved balancedness for 4 out of 5 subjects.
This paper presents a design of a non-player character (AI) for promoting balancedness in use of body segments when engaging in full-body motion gaming. In our experiment, we settle a battle between the proposed AI and a player by using FightingICE, a fighting game platform for AI development. A middleware called UKI is used to allow the player to control the game by using body motion instead of the keyboard and mouse. During gameplay, the proposed AI analyze health states of the player; it determines its next action by predicting how each candidate action, recommended by a Monte-Carlo tree search algorithm, will induce the player to move, and how the player's health tends to be affected. Our result demonstrates successful improvement in balancedness in use of body segments on 4 out of 5 subjects.