Understanding and mapping pleasure, arousal and dominance social signals to robot-avatar behavior

We present an analysis of the pleasure, arousal, and dominance social signals inferred from people's faces, and how, despite their noisy nature, these can be used to drive a model of theory-based interventions for a robot-avatar agent in a working space. The analysis let emerge clearly the need for data pre-filtering and per-user calibration. The proposed post-processing method helps quantify the parameters needed to control the frequency of intervention of the agent; still leaving the experimenter with a run-time adjustable global control of its sensitivity.