A specially-equipped Roomba robot vacuum cleaner can now sense human emotional states. University of Calgary researchers published their results in a paper titled “Using Bio-electrical Signals to Influence the Social Behaviours of Domesticated Robots.”
Using a special headband to capture bioelectric signals from the forehead of a human user, the system collects this data and then infers stress from muscle tension readings. Their control software reinterprets natural muscle tension as estimating the user’s stress level; the more muscle tension, the more stress is inferred.
“Two distinct robotic behaviours corresponding to two extreme emotional states, either relaxed or stressed, are triggered when the stress reading reach a threshold. Robot actions are then influenced by these stress readings. When a person shows high stress (~levels 3 & 4), the robot enters its cleaning mode but moves away from the user so as not annoy them. When a person is relaxed (~level 1), the robot (if cleaning) approaches the person and then stops, simulating a pet sitting next to its owner. If the reading is in between these two levels, the robot continues operating in its current mode until the stress reading reaches a threshold.”