Force Sensor

Haptics provides a natural and intuitive channel of communication during the interaction of two humans in complex physical tasks, such as joint object transportation. However, despite the utmost importance of touch in physical interactions, the use of haptics is underrepresented when developing intelligent systems. This study explores the prominence of haptic data to extract information about underlying interaction patterns within human-human cooperation. For this purpose, we design salient haptic features describing the collaboration quality within a physical dyadic task and investigate the use of these features to classify the interaction patterns. We categorize the interaction into four discrete behavior classes. These classes describe whether the partners work in harmony or face conflicts while jointly transporting an object through translational or rotational movements. We test the proposed features on a physical human-human interaction (pHHI) dataset, consisting of data collected from 12 human dyads. Using these data, we verify the salience of haptic features by achieving a correct classification rate over 91% using a Random Forest classifier.