Proactive Human-Robot Collaboration with Interaction Primitives


This paper introduces our initial investigation into the problem of providing a semi-autonomous robot collaborator with anticipative capabilities to predict the upcoming human actions. Predictive robot behavior is a desired characteristic of robot collaborators that lead to fluid and faster interactions. We are particularly interested in improving reactive methods that rely on human action recognition to activate a corresponding robot movement. Action recognition invariably causes delay in the robot’s response, and the goal of our method is to minimize this delay by predicting the next human action and pre-triggering the corresponding robot motions. The prediction is achieved by using a lookup table containing variations of assembly sequences, previously demonstrated by different users.The method uses the nearest neighbor sequence in the table that matches the actual sequence of human actions. At the movement level, our method uses a probabilistic representation of interaction primitives to generate the robot trajectories. The method is demonstrated using a 7 degree-of-freedom lightweight(DoF) arm equipped with a 5-finger hand on an assembly task consisting of 17 steps.

International Workshop on Human-Friendly Robotics (HFR)