Data-driven Grip Force Variation in Robot-Human Handovers

Abstract-- Handovers frequently occur in our social environments, making it imperative for a collaborative robotic system to master the skill of handover. In this work, we aim to investigate the relationship between the grip force variation for a human giver and the sensed interaction force-torque in human-human handovers, utilizing a data-driven approach. A Long-Short Term Memory (LSTM) network was trained to use the interaction force-torque in a handover to predict the human grip force variation in advance. In a handover, the giver holds and carries the object It was shown that a linear relation exists between load shared to a suitable, pre-determined handover location while the and grip force of the human giver. This finding was used in taker reaches for the object.