Learning generalizable control programs

IEEE Transactions on Autonomous Mental Development

Volumn 3, Issue 3, 2011, Pages 216-231

  Hart, Stephen ^a   Grupen, Roderic ^b  

^a ISTITUTO ITALIANO DI TECNOLOGIA   (Italy)

^b The Manning College of Information and Computer Sciences   (United States)

Author keywords

Cognitive architectures; generalization; incremental learning; intrinsic motivation; reinforcement learning; schema

Indexed keywords

COGNITIVE ARCHITECTURES; GENERALIZATION; INCREMENTAL LEARNING; INTRINSIC MOTIVATION; SCHEMA;

COGNITIVE SYSTEMS; MOTIVATION; REINFORCEMENT; REINFORCEMENT LEARNING;

ROBOTS;

EID: 80052879447     PISSN: 19430604     EISSN: None     Source Type: Journal    
DOI: 10.1109/TAMD.2010.2103311     Document Type: Conference Paper

References (36)

1. M. Asada, K. MacDorman, H. Ishiguro, and Y. Kuniyoshi, "Cognitive developmental robotics as a new paradigm for the design of humanoid robots," Robot. Autonom. Syst., vol. 37, no. 2, pp. 185-193, 2001. (Pubitemid 33039294)
2. N. Bernstein, , M. Latash and M. Turvey, Eds., "On dexterity and its development," in Dexterity and Its Development. Mahwah, NJ: Erlbaum, 1996.
3. A. Billard, S. Calinon, R. Dillmann, and S. Schaal, , B. Siciliano and O. Khatib, Eds., "Robot programming by demonstration," in Handbook of Robotics. Secaucus, NJ: Springer, 2008, pp. 1371-1394.
4. C. Connolly, J. Burns, and R. Weiss, "Path planning using laplace's equation," in Proc. IEEE Conf. Robotics Autom. (ICRA), Cincinnati, OH, 1990.
5. C. Geib, K. Mourão, R. Petrick, N. Pugeault, M. Steedman, N. Krüger, and F. Wörgötter, "Object action complexes as an interface for planning and robot control," in Proc. IEEE-RAS Int. Conf. Human. Robot., Genoa, Italy, 2006.
6. J. J. Gibson, "The theory of affordances," in Perceiving, Acting and Knowing: Toward an Ecological Psychology. Hillsdale, NJ: Erlbaum, 1977, pp. 67-82.
7. S. Hart, "An intrinsic reward for affordance exploration," in Proc. 8th IEEE Int. Conf. Develop. Learn. (ICDL), Shanghai, China, 2009.
8. S. Hart and R. Grupen, "Natural task decomposition with intrinsic potential fields," in Proc. 2007 Int. Conf. Intell. Robot. Syst. (IROS), San Diego, CA, 2007.
9. S. Hart, S. Sen, and R. Grupen, "Generalization and transfer in robot control," in Proc. 8th Int. Conf. Epig. Robot. (Epirob08), Brighton, U.K., 2008.
10. S. Hart, S. Sen, and R. Grupen, "Intrinsically motivated hierarchical manipulation," in Proc. 2008 IEEE Conf. Robot. Autom. (ICRA), Pasadena, CA, 2008.
11. S. Hart, S. Sen, S. Ou, and R. Grupen, "The control basis api -Alayered software architecture for autonomous robot learning," in Proc. 2009 Workshop Software Develop. Integration Robot. (SDIR), Kobe, Japan, 2009.
12. S. W. Hart, "The development of hierarchical knowledge in robot systems," Ph.D. thesis, Dept. Comput. Sci., Univ. Massachusetts Amherst, Amherst, MA, 2009.
13. M. Huber, "A hybrid architecture for adaptive robot control," Ph.D. thesis, Dept. Comput. Sci., Univ. Massachusetts Amherst, Amherst, MA, 2000.
14. D. Koditschek and E. Rimon, "Robot navigation functions on manifolds with boundary," Adv. Appl. Math., vol. 11, no. 4, pp. 412-442, Dec. 1990.
15. D. Kraft, N. Pugeault, E. Baseski, M. Popović, D. Kragic, S. Kalkan, F. Wörgötter, and N. Krüger, "Birth of the object: Detection of objectness and extraction of shape through object action complexes," in Proc. 2008 Int. Conf. Cogn. Syst., Karlsruhe, Germany, 2008.
16. N. Krüger, J. Piater, F. Wörgötter, C. Geib, R. Petrick, M. Steedman, A. Ude, T. Asfour, D. Kraft, D. Omrcen, B. Hommel, A. Agostino, D. Kragic, J. Eklundh, V. Kruger, and R. Dillmann, A formal definition of object action complexes and examples at different levels of the process hierarchy 2009 [Online]. Available: http://www.paco-plus.org
17. M. Lungarella, G. Metta, R. Pfeifer, and G. Sandini, "Developmental robotics: A survey," Connect. Sci., vol. 15, no. 4, 2003.
18. G. Metta, P. Fitzpatrick, and L. Natale, "Yarp: Yet another robot platform," in Int. J. Adv. Robot. Syst., Special Issue Software Develop. Integr. Robot., Mar. 2006.
19. Microsoft Robotics Developers Studio Microsoft Co., 2008 [Online]. Available: http://msdn.microsoft.com/en-us/robotics/
20. L. Montesano, M. Lopes, A. Bernardino, and J. Santos-Victor, "Learning object affordances: From sensory-motor coordination to imitation," IEEE Trans. Robot., vol. 24, no. 1, pp. 15-26, Feb. 2008. (Pubitemid 351411194)
21. Y. Nakamura, Advanced Robotics: Redundancy and Optimization. Reading, MA: Addison-Wesley, 1991.
22. A. Y. Ng and S. Russell, "Algorithms for inverse reinforcement learning," in Proc. 17th Int. Conf. Mach. Learn., Stanford, CA, 2000.
23. J. S. Ostroff and W. M. Wonham, "A temporal logic approach to real time control," in Proc. 24th IEEE Conf. Decision Contr., Dec. 1985, vol. 24, pp. 656-657. (Pubitemid 16598326)
24. J. Piaget, The Origins of Intelligence in Children. Madison, CT: Int. Universities Press, 1952.
25. R. Platt, A. H. Fagg, and R. Grupen, "Nullspace composition of control laws for grasping," in Proc. Int. Conf. Intell. Robot. Syst. (IROS), Laussane, Switzerland, 2002.
26. J. Quinlan, C4.5: Programs For Machine Learning. San Mateo, CA: Morgan Kaufmann, 1993.
27. E. Rimon and D. Koditschek, "Exact robot navigation using artificial potential functions," IEEE Trans. Robot. Autom., vol. 8, no. 5, pp. 501-518, Oct. 1992. (Pubitemid 23580959)
28. K. Rohanimanesh and S. Mahadevan, "Coarticulation: An approach for generating concurrent plans in markov decision processes," in Proc. 22nd Int. Conf. Mach. Learn. (ICML-2005), Bonn, Germany, 2005.
29. E. Şahin, M. Çakmak, M. Dogar, E. Ugur, and G. Üçoluk, "To afford of not to afford: A formalization of affordances toward affordance-based robot control," Adapt. Behav., vol. 4, no. 15, pp. 447-472, 2007. (Pubitemid 350017595)
30. G. Sandini, G. Metta, and J. Konczak, "Human sensori-motor development and artificial systems," in Proc. AIR & IHAS, 1997.
31. S. Schaal, "Is imitation learning the route to humanoid robots?," Trends Cogn. Sci., vol. 3, no. 6, pp. 233-242, 1999. (Pubitemid 29261903)
32. R. Sutton and A. Barto, Reinforcement Learning. Cambridge, MA: MIT Press, 1998.
33. R. Sutton, D. Precup, and S. Singh, "Between mdps and semi-mdps: A framework for temporal abstraction in reinforcement learning," Artif. Intell., vol. 112, no. 1-2, pp. 181-211, Aug. 1999. (Pubitemid 32079890)
34. J. Uppala, D. Karuppiah, M. Brewer, C. Ravela, and R. Grupen, "On viewpoint control," in Proc. Int. IEEE Conf. Robot. Autom., 2002.
35. D. Watkins and P. Dayan, "q-learning," Mach. Learn., vol. 8, no. 3,4, pp. 279-292, 1992.
36. T. Yoshikawa, "Manipulability of robotic mechanisms," Int. J. Robot. Res., vol. 4, no. 2, pp. 3-9, Jun. 1, 1985.