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, andhow, despite their noisy nature, these can be used to drive amodel of theory-based interventions for a robot-avatar agentin a working space. The analysis let emerge clearly the needfor data pre-filtering and per-user calibration. The proposedpost-processing method helps quantify the parameters neededto control the frequency of intervention of the agent; still leavingthe experimenter with a run-time adjustable global control of itssensitivity.