Interactive Task Learning: Humans, Robots, and Agents Acquiring New Tasks through Natural Interactions

by Kevin A. Gluck, John E. Laird

Overview

Experts from a range of disciplines explore how humans and artificial agents can quickly learn completely new tasks through natural interactions with each other.

Humans are not limited to a fixed set of innate or preprogrammed tasks. We learn quickly through language and other forms of natural interaction, and we improve our performance and teach others what we have learned. Understanding the mechanisms that underlie the acquisition of new tasks through natural interaction is an ongoing challenge. Advances in artificial intelligence, cognitive science, and robotics are leading us to future systems with human-like capabilities. A huge gap exists, however, between the highly specialized niche capabilities of current machine learning systems and the generality, flexibility, and in situ robustness of human instruction and learning. Drawing on expertise from multiple disciplines, this Strüngmann Forum Report explores how humans and artificial agents can quickly learn completely new tasks through natural interactions with each other.

The contributors consider functional knowledge requirements, the ontology of interactive task learning, and the representation of task knowledge at multiple levels of abstraction. They explore natural forms of interactions among humans as well as the use of interaction to teach robots and software agents new tasks in complex, dynamic environments. They discuss research challenges and opportunities, including ethical considerations, and make proposals to further understanding of interactive task learning and create new capabilities in assistive robotics, healthcare, education, training, and gaming.

Contributors
Tony Belpaeme, Katrien Beuls, Maya Cakmak, Joyce Y. Chai, Franklin Chang, Ropafadzo Denga, Marc Destefano, Mark d'Inverno, Kenneth D. Forbus, Simon Garrod, Kevin A. Gluck, Wayne D. Gray, James Kirk, Kenneth R. Koedinger, Parisa Kordjamshidi, John E. Laird, Christian Lebiere, Stephen C. Levinson, Elena Lieven, John K. Lindstedt, Aaron Mininger, Tom Mitchell, Shiwali Mohan, Ana Paiva, Katerina Pastra, Peter Pirolli, Roussell Rahman, Charles Rich, Katharina J. Rohlfing, Paul S. Rosenbloom, Nele Russwinkel, Dario D. Salvucci, Matthew-Donald D. Sangster, Matthias Scheutz, Julie A. Shah, Candace L. Sidner, Catherine Sibert, Michael Spranger, Luc Steels, Suzanne Stevenson, Terrence C. Stewart, Arthur Still, Andrea Stocco, Niels Taatgen, Andrea L. Thomaz, J. Gregory Trafton, Han L. J. van der Maas, Paul Van Eecke, Kurt VanLehn, Anna-Lisa Vollmer, Janet Wiles, Robert E. Wray III, Matthew Yee-King

Product Details

ISBN-13:	9780262038829
Publisher:	MIT Press
Publication date:	09/10/2019
Series:	Strüngmann Forum Reports , #26
Pages:	354
Product dimensions:	9.10(w) x 6.00(h) x 1.00(d)
Age Range:	18 Years

About the Author

Kevin A. Gluck is a Principal Cognitive Scientist at the U.S. Air Force Research Laboratory.

John E. Laird is John L. Tishman Professor of Engineering in the Computer Science and Engineering Department at the University of Michigan.

Table of Contents

Preface ix

List of Contributors xi

1 Looking Forward to Interactive Task Learning Kevin A. Gluck John E. Laird 1

2 Framing the Problem of Interactive Task Learning Tom M. Mitchell Simon Garrod John E. Laird Stephen C. Levinson Kenneth R. Koedinger 9

Knowledge

3 Functional Knowledge Requirements for Interactive Task Learning Robert E. Wray III Niels A. Taatgen Christian Lebiere Katerina Pastra Peter Pirolli Paul S. Rosenbloom Matthias Scheutz Terrence C. Stewart Janet Wiles 19

4 What People Learn from Instruction Christian Lebiere 53

5 An Ontological Perspective on Interactive Task Learning Charles Rich 63

6 The Representation of Task Knowledge at Multiple Levels of Abstraction Niels A. Taatgen 75

Interaction

7 Interaction for Task Instruction and Learning Andrea L. Thomaz Elena Lieven Maya Cakmak Joyce Y. Chai Simon Garrod Wayne D. Gray Stephen C. Levinson Ana Paiva Nele Russwinkel 91

8 Natural Forms of Purposeful Interaction among Humans: What Makes Interaction Effective? Stephen C. Levinson 111

9 Teaching Robots New Tasks through Natural Interaction Joyce Y. Chai Maya Cakmak Candace L. Sidner 127

10 The Essence of Interaction in Boundedly Complex, Dynamic Task Environments Wayne D. Gray John K. Lindstedt Catherine Sibert Matthew-Donald D. Sangster Roussel Rahman Ropafadzo Denga Marc Destefano 147

Instruction

11 Task Instruction Julie A. Shah Kevin A. Gluck Tony Belpaeme Kenneth R. Koedinger Katharina J. Rohlfing Han L. J. van der Maas Paul Van Eecke Kurt VanLehn Anna-Lisa Vollmer Matthew Yee-King 169

12 What Do Human Tutors Do? Kurt VanLehn 193

13 Strategies for Interactive Task Learning and Teaching Katrien Beuls Luc Steels Paul Van Eecke 207

14 Creativity and Feedback: Designing Systems to Support Student Learning and Improve Instruction Arthur Still Matthew Yee-King Mark d'Inverno 217

Learning New Tasks

15 Learning Task Knowledge Dario D. Salvucci John E. Laird Franklin Chang Kenneth D. Forbus Parisa Kordjamshidi Tom M. Mitchell Shiwali Mohan Michael Spranger Suzanne Stevenson Andrea Stocco J. Gregory Trafton 237

16 Early Developing Prerequisites for Human Interactive Task Learning Franklin Chang 259

17 Characteristics of the Learning Problem in Situated Interactive Task Learning John E. Laird Shiwali Mohan James Kirk Aaron Mininger 273

Ethical Considerations

18 Ethical Aspects and Challenges for Interactive Task Learning Matthias Scheutz 295

Bibliography 305

Subject Index 333

Strüngmann Forum Report Series 339