Communicative Lifting Actions in Human-Humanoid Interaction

Passing an object to someone else is one of the simplest collaborative actions. However, it entails a high degree of coordination between the two partners. The efficiency of the result relies heavily on the non-verbal communication associated to the passer's motion. The kinematic properties of the movement convey to the receiver implicit information about when, where and what is going to be passed. In this paper we focus on the "what", by proposing a simple architecture which allows a humanoid robot to autonomously plan lifting movements which implicitly inform the human partner of the weight of the lifted object. We implemented the system on the humanoid robot iCub in a "robot waiter" scenario and experimentally verified the readability of the robot motion. We suggest that the implementation of such human-aware motion planning could ensure a seamless and natural interaction with nonexpert users, yielding in turn to safer and more efficient object passing.