Learning about objects with human teachers

ABSTRACT

A general learning task for a robot in a new environment is to learn about objects and what actions/effects they afford. To approach this, we look at ways that a human partner can intuitively help the robot learn, Socially Guided Machine Learning. We present experiments conducted with our robot, Junior, and make six observations characterizing how people approached teaching about objects. We show that Junior successfully used transparency to mitigate errors. Finally, we present the impact of "social" versus "non-social" data sets when training SVM classifiers.

REFERENCES

• 1: Christopher G. Atkeson , Stefan Schaal, Robot Learning From Demonstration, Proceedings of the Fourteenth International Conference on Machine Learning, p.12-20, July 08-12, 1997
• 2: Bruce Blumberg , Marc Downie , Yuri Ivanov , Matt Berlin , Michael Patrick Johnson , Bill Tomlinson, Integrated learning for interactive synthetic characters, Proceedings of the 29th annual conference on Computer graphics and interactive techniques, July 23-26, 2002, San Antonio, Texas
• 3: S. Calinon and A. Billard. What is the teacher's role in robot programming by demonstration? - Toward benchmarks for improved learning. Interaction Studies. Special Issue on Psychological Benchmarks in Human-Robot Interaction, 8(3), 2007.
• 4: Sonia Chernova , Manuela Veloso, Multi-thresholded approach to demonstration selection for interactive robot learning, Proceedings of the 3rd ACM/IEEE international conference on Human robot interaction, March 12-15, 2008, Amsterdam, The Netherlands [doi>10.1145/1349822.1349852]
• 5: Sonia Chernova , Manuela Veloso, Teaching multi-robot coordination using demonstration of communication and state sharing, Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems, May 12-16, 2008, Estoril, Portugal
• 6: P. M. Greenfield. Theory of the teacher in learning activities of everyday life. In B. Rogoý and J. Lave, editors, Everyday cognition: its development in social context. Harvard University Press, Cambridge, MA, 1984.
• 7: D. H. Grollman and O. C. Jenkins. Sparse incremental learning for interactive robot control policy estimation. In In IEEE International Conference on Robotics and Automation, 2008.
• 8: F. Kaplan, P.-Y. Oudeyer, E. Kubinyi, and A. Miklosi. Robotic clicker training. Robotics and Autonomous Systems, 38(3-4):197--206, 2002.
• 9: Y. Kuniyoshi, M. Inaba, and H. Inoue. Learning by watching: Extracting reusable task knowledge from visual observation of human performance. IEEE Transactions on Robotics and Automation, 10:799--822, 1994.
• 10: R. Maclin, J. Shavlik, L. Torrey, T. Walker, and E. Wild. Giving advice about preferred actions to reinforcement learners via knowledge-based kernel regression. In Proc. of the The Twentieth National Conference on Artificial Intelligence, 2005.
• 11: L. Montesano, M. Lopes, A. Bernardino, and J. Santos-Victor. Learning object affordances: From sensory-motor coordination to imitation. IEEE Transactions on Robotics, 24:15--26, 2008.
• 12: Monica N. Nicolescu , Maja J. Mataric, Natural methods for robot task learning: instructive demonstrations, generalization and practice, Proceedings of the second international joint conference on Autonomous agents and multiagent systems, July 14-18, 2003, Melbourne, Australia [doi>10.1145/860575.860614]
• 13: L. M. Saksida, S. M. Raymond, and D. S. Touretzky. Shaping robot behavior using principles from instrumental conditioning. Robotics and Autonomous Systems, 22(3/4):231, 1998.
• 14: Greg Schohn , David Cohn, Less is More: Active Learning with Support Vector Machines, Proceedings of the Seventeenth International Conference on Machine Learning, p.839-846, June 29-July 02, 2000
• 15: W. D. Smart and L. P. Kaelbling. Effective reinforcement learning for mobile robots. In In Proc. of the IEEE International Conference on Robotics and Automation, pages 3404--3410, 2002.
• 16: A. L. Thomaz and C. Breazeal. Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance. In Proc. of the 21st National Conference on Artificial Intel ligence, 2006.
• 17: Andrea L. Thomaz , Cynthia Breazeal, Experiments in socially guided exploration: lessons learned in building robots that learn with and without human teachers, Connection Science, v.20 n.2-3, p.91-110, June 2008 [doi>10.1080/09540090802091917]
• 18: Andrea L. Thomaz , Cynthia Breazeal, Teachable robots: Understanding human teaching behavior to build more effective robot learners, Artificial Intelligence, v.172 n.6-7, p.716-737, April, 2008 [doi>10.1016/j.artint.2007.09.009]
• 19: R. Voyles and P. Khosla. A multi-agent system for programming robotic agents by human demonstration. In Proc. of AI and Manufacturing Research Planning Workshop, 1998.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.9 Robotics

General Terms:
Experimentation, Human Factors

Keywords:
interactive machine learning, social robot learning