Mixed initiative in interactive robotic learning

Peltason, Julia and Lütkebohle, Ingo and Wrede, Britta and Hanheide, Marc (2009) Mixed initiative in interactive robotic learning. In: Mixed Initiative Workshop on Improving Human-Robot Communication with Mixed-Initiative and Context-Awareness at the 18th IEEE International Symposium on Robot and Human Interactive Communication, Sept. 27 2009-Oct. 2 2009, Toyama International Conference Center, Japan.

Full content URL: http://dx.doi.org/

Documents
Peltason2009-Mixed_Initiative_in_Interactive_Robotic_Learning[1].pdf
[img]
[Download]
[img]
Preview
PDF
Peltason2009-Mixed_Initiative_in_Interactive_Robotic_Learning[1].pdf - Whole Document

132kB
Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

In learning tasks, interaction is mostly about the exchange
of knowledge. The interaction process shall be governed on the one hand by the knowledge the tutor wants to convey and on the other by the lacks of knowledge of the learner. In human-robot interaction (HRI), it is usually the human demonstrating or explicitly verbalizing her knowl-
edge and the robot acquiring a respective representation. The ultimate goal in interactive robot learning is thus to enable inexperienced, un- trained users to tutor robots in a most natural and intuitive manner.
This goal is often impeded by a lack of knowledge of the human about the internal processing and expectations of the robot and by the inflexibility of the robot to understand open-ended, unconstrained tutoring or demonstration. Hence, we propose mixed-initiative strategies to allow both to mutually contribute to the interactive learning process as
a bi-directional negotiation about knowledge. Along this line this paper discusses two initially different case studies on object manipulation and learning of spatial environments. We present different styles of mixed-
initiative in these scenarios and discuss the merits in each case.

Additional Information:In learning tasks, interaction is mostly about the exchange of knowledge. The interaction process shall be governed on the one hand by the knowledge the tutor wants to convey and on the other by the lacks of knowledge of the learner. In human-robot interaction (HRI), it is usually the human demonstrating or explicitly verbalizing her knowl- edge and the robot acquiring a respective representation. The ultimate goal in interactive robot learning is thus to enable inexperienced, un- trained users to tutor robots in a most natural and intuitive manner. This goal is often impeded by a lack of knowledge of the human about the internal processing and expectations of the robot and by the inflexibility of the robot to understand open-ended, unconstrained tutoring or demonstration. Hence, we propose mixed-initiative strategies to allow both to mutually contribute to the interactive learning process as a bi-directional negotiation about knowledge. Along this line this paper discusses two initially different case studies on object manipulation and learning of spatial environments. We present different styles of mixed- initiative in these scenarios and discuss the merits in each case.
Keywords:Robotics, Human-robot interaction
Subjects:H Engineering > H670 Robotics and Cybernetics
Divisions:College of Science > School of Computer Science
ID Code:6923
Deposited On:07 Jan 2013 08:58

Repository Staff Only: item control page