Towards Human Haptic Gesture Interpretation for Robotic Systems
This work aims to improve the efficiency and communicativeness of physical human-robot interactions by enabling robots to better interpret human touch gestures, which is a problem for robotic systems interacting with humans.
This paper addresses the challenge of interpreting human haptic gestures for robotic systems by proposing four touch gesture classes and collecting an extensive force dataset using a common pHRI robotic arm's internal wrist force-torque sensor. The study demonstrates high classification accuracies, with neural network classifiers on raw data outperforming other feature set and algorithm combinations.
Physical human-robot interactions (pHRI) are less efficient and communicative than human-human interactions, and a key reason is a lack of informative sense of touch in robotic systems. Interpreting human touch gestures is a nuanced, challenging task with extreme gaps between human and robot capability. Among prior works that demonstrate human touch recognition capability, differences in sensors, gesture classes, feature sets, and classification algorithms yield a conglomerate of non-transferable results and a glaring lack of a standard. To address this gap, this work presents 1) four proposed touch gesture classes that cover an important subset of the gesture characteristics identified in the literature, 2) the collection of an extensive force dataset on a common pHRI robotic arm with only its internal wrist force-torque sensor, and 3) an exhaustive performance comparison of combinations of feature sets and classification algorithms on this dataset. We demonstrate high classification accuracies among our proposed gesture definitions on a test set, emphasizing that neural net-work classifiers on the raw data outperform other combinations of feature sets and algorithms. The accompanying video is here: https://youtu.be/gJPVImNKU68