In human-human interactions, individuals naturally achieve fluency by anticipating the partner’s actions. This predictive ability is largely lacking in collaborative robots, leading to inefficient human-robot interactions. Fluent meshing in human-robot collaboration requires the robot to make its intentions clear to its human collaborator. We propose a unified generative model of human reaching motions that allows the robot to (a) infer human intent, and then (b) plan its motion to be legible, or intent-expressive. We conducted a study on human reaching motion and constructed an elliptical motion model that is shown to yield a good fit to empirical data. In future studies, we plan to confirm the effectiveness of this model in predicting human intent and conveying robot intent for achieving fluency in human-robot handovers.
A Study of Reaching Motions for Collaborative Human-Robot Interaction
Springer Proceedings in Advanced Robotics
International Symposium on Experimental Robotics ; 2018 ; Buenos Aires, Argentina November 05, 2018 - November 08, 2018
Proceedings of the 2018 International Symposium on Experimental Robotics ; Kapitel : 50 ; 584-594
2020-01-23
11 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Modeling Variability in Reaching Motions
SAE Technical Papers | 2001
|Human centric collaborative workplace: the human robot interaction system perspective
BASE | 2023
|