ISBN: 9780262349420 | 354 pp. | September 2018

Interactive Task Learning


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.

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

Table of Contents

  1. In Memoriam
  2. Preface
  3. List of Contributors
  4. 1. Looking Forward to Interactive Task Learning
  5. 2. Framing the Problem of Interactive Task Learning
  6. I. Knowledge
  7. 3. Functional Knowledge Requirements for Interactive Task Learning
  8. 4. What People Learn from Instruction
  9. 5. An Ontological Perspective on Interactive Task Learning
  10. 6. The Representation of Task Knowledge at Multiple Levels of Abstraction
  11. II. Interaction
  12. 7. Interaction for Task Instruction and Learning
  13. 8. Natural Forms of Purposeful Interaction among Humans: What Makes Interaction Effective?
  14. 9. Teaching Robots New Tasks through Natural Interaction
  15. 10. The Essence of Interaction in Boundedly Complex, Dynamic Task Environments
  16. III. Instruction
  17. 11. Task Instruction
  18. 12. What Do Human Tutors Do?
  19. 13. Strategies for Interactive Task Learning and Teaching
  20. 14. Creativity and Feedback
  21. IV. Learning New Tasks
  22. 15. Learning Task Knowledge
  23. 16. Early Developing Prerequisites for Human Interactive Task Learning
  24. 17. Characteristics of the Learning Problem in Situated Interactive Task Learning
  25. 18. Ethical Aspects and Challenges for Interactive Task Learning
  26. Bibliography
  27. Subject Index
  28. Strüngmann Forum Report Series