Active memory-based interaction strategies for learning-enabling behaviors

Hanheide, Marc and Sagerer, Gerhard (2008) Active memory-based interaction strategies for learning-enabling behaviors. In: RO-MAN 2008 - The 17th IEEE International Symposium on Robot and Human Interactive Communication, August 1-3 2008, Munich.

Full content URL: http://dx.doi.org/10.1109/ROMAN.2008.4600650

Documents
Hanheide2008-Active_memory-based_interaction_strategies_for_learning-enabling_behaviors[1].pdf

Request a copy
[img] PDF
Hanheide2008-Active_memory-based_interaction_strategies_for_learning-enabling_behaviors[1].pdf - Whole Document
Restricted to Repository staff only

273kB
Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

Despite increasing efforts in the field of social
robotics and interactive systems integrated and fully autonomous
robots which are capable of learning from interaction
with inexperienced and non-expert users are still a rarity.
However, in order to tackle the challenge of learning by
interaction robots need to be equipped with a set of basic
behaviors and abilities which have to be coupled and combined
in a flexible manner. This paper presents how a recently
proposed information-driven integration concept termed “active
memory” is adopted to realize learning-enabling behaviors for
a domestic robot. These behaviors enable it to (i) learn about its
environment, (ii) interact with several humans simultaneously,
and (iii) couple learning and interaction tightly. The basic
interaction strategies on the basis of information exchange
through the active memory are presented. A brief discussion
of results obtained from live user trials with inexperienced
users in a home tour scenario underpin the relevance and
appropriateness of the described concepts.

Additional Information:Despite increasing efforts in the field of social robotics and interactive systems integrated and fully autonomous robots which are capable of learning from interaction with inexperienced and non-expert users are still a rarity. However, in order to tackle the challenge of learning by interaction robots need to be equipped with a set of basic behaviors and abilities which have to be coupled and combined in a flexible manner. This paper presents how a recently proposed information-driven integration concept termed “active memory” is adopted to realize learning-enabling behaviors for a domestic robot. These behaviors enable it to (i) learn about its environment, (ii) interact with several humans simultaneously, and (iii) couple learning and interaction tightly. The basic interaction strategies on the basis of information exchange through the active memory are presented. A brief discussion of results obtained from live user trials with inexperienced users in a home tour scenario underpin the relevance and appropriateness of the described concepts.
Keywords:Robotics, Human-robot interaction, intelligent robots, learning (artificial intelligence), service robots, active memory-based interaction strategies, autonomous robots, domestic robot, information-driven integration, interaction robots, interactive systems, learning-enabling behaviors, social robotics
Subjects:H Engineering > H670 Robotics and Cybernetics
Divisions:College of Science > School of Computer Science
ID Code:6928
Deposited On:07 Jan 2013 10:44

Repository Staff Only: item control page