From Action Perception to Joint Actions: Learning from Joint Handover Actions of Human Dyads for Robotic Actions and Human-Robot Interactions
The objective is to investigate joint action coordination in human dyads during handover tasks. Insights into joint action control can advance control mechanisms for joint actions in mixed (i.e., robot-human) dyads. In our experiments, we measure kinematics of reach and grasp as well as grasp force dynamics during handover tasks when systematically varying the composition of the dyads (e.g., age of the partners) and properties of the objects. Advanced analysis (e.g., dimensionality reduction) will be used to understand reach and grasp kinematics and, therefore, predict action consequences (e.g., handover position, force scaling), which facilitates joint action. Action prediction will be simulated and tested.