Stress detection for implicit human-robot co-operation

An online heart rate variability analysis to infer the mental stress of a human engaged in a task has been presented. This technique involves real-time heart rate monitoring, signal processing using both Fourier Transform and Wavelet Transform, and inferring the stress condition based on the level of activation of the sympathetic and parasympathetic nervous systems. The standard deviations of the Wavelet coefficients for a particular frequency band were compared for stressed and reference data. When stressed, the standard deviation in the sympathetic frequency band (0.0625-0.125 Hz) was found to increase and the standard deviation in the parasympathetic frequency band (0.25-0.3125 Hz) was found to decrease. This stress detection technique is expected to be useful in the future human-robot cooperation activities.