An Embodied Approach for Joint Action Collaboration with Humanoid Robots

Kothig A., Aroyo AM., Dautenhahn K.
In HRI 2022 Workshop on Joint Action, Adaptation, and Entrainment in Human-Robot Interaction (JAAE)

Abstract

Joint action problems remain a difficult endeavor when social robots are involved. The level of patience that a person has when interacting with a robot has been shown to vary based on their expectations of the robot's capabilities and the difficulty of the task. Social robots, especially humanoid ones, require an additional level of consideration when designing behaviors and interactions to meet such expectations. We aim to explore an approach rooted in the perceived embodiment of a humanoid robot to improve the interaction experience. This manuscript outlines previous work and inspirations for our development thus far. By utilizing a definition of embodiment, we have identified four mutual perturbatory channels that humanoid robots share with people. Through an experimental joint action scenario, we aim to quantify the bandwidth of these perturbatory channels, which we can use to further maximize the embodiment of the robot and improve the user-experience of interaction with the robot.

Images

The humanoid robotics platform iCub. A robot with 53 actuated degrees of freedom distributed throughout its body. The robot is capable of grasping objects, speech synthesis, sharing mutual gaze, and expressing a range of high-level emotions through the multi-color LEDs under the face-plate.

(Top) Game start state, (Bottom) Game goal state, for a configuration of n = 4, k = 3, where n is the number of disks and k is the number of pegs. The Bicolor Towers is a variation of the classic children’s puzzle game, Tower of Hanoi. Similar in rules to the original, disks are moved one by one between the pegs while maintaining a rule that no disk has a strictly larger disk on top of it. Which is to say, a disk can move from peg u to peg v if and only if the peg v is empty or the top disk of the peg is of equal or larger size. This variation adds a level of complexity, such that any person who is already familiar with the simple recursive solution to the Tower of Hanoi game may not immediately know how to arrive at this version’s solution, and therefore may leverage the robot for some assistance.

---

How to cite?

@inproceedings{kothig2022embodied, 
    title={An Embodied Approach for Joint Action Collaboration with Humanoid Robots}, 
    author={Kothig, Austin and Aroyo, Alexander M. and Dautenhahn, Kerstin},
    booktitle={HRI 2022 Workshop on Joint Action, Adaptation, and Entrainment in Human-Robot Interaction (JAAE)}, 
    publisher={IEEE}, 
    month={March},
    year={2022}
}

---

Downloads

Download Paper