Abstract
A new approach to building robots with anticipatory behavior is presented. This approach is based on analogy with a single episode from the past experience of the robot. The AMBR model of analogy-making is used as a basis, but it is extended with new agent-types and new mechanisms that allow anticipation related to analogical transfer. The role of selective attention on retrieval of memory episodes is tested in a series of simulations and demonstrates the context sensitivity of the AMBR model. The results of the simulations clearly demonstrated that endowing robots with analogy-based anticipatory behavior is promising and deserves further investigation.
This work has been supported by the MIND RACES project funded by the 6th FP of the EC (IST Contract 511931).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Baldassarre, G.: Planning with Neural Networks and Reinforcement Learning. PhD Thesis, Computer Science Department, University of Essex, Colchester, UK (2002)
Baldassarre, G.: Forward and Bidirectional Planning Based on Reinforcement Learning and Neural Networks in a Simulated Robot. In: Butz, M., Sigaud, O., Gérard, P. (eds.) Adaptive Behaviour in Anticipatory Learning Systems, pp. 179–200. Springer, Heidelberg (2003)
Brooks, R.A.: How to build complete creatures rather than isolated cognitive simulators. In: VanLehn, K. (ed.) Architectures for Intelligence, pp. 225–239. Lawrence Erlbaum Assosiates, Hillsdale (1991)
Butz, M.V., Goldberg, D.E., Stolzmann, W.: The anticipatory classifier system and genetic generalization. Natural Computing 1, 427–467 (2002)
Butz, M.V., Goldberg, D.E.: Generalized state values in an anticipatory learning classifier system. In: Butz, M., Sigaud, O., Gérard, P. (eds.) Anticipatory behavior in adaptive learning systems, pp. 282–301. Springer, Heidelberg (2003)
Gentner, D.: Structure-mapping: A theoretical framework for analogy. Cognitive Science 7, 155–170 (1983)
Hofstadter, D.R.: Fluid Concepts and Creative Analogies: Computer Models of the Fundamental Mechanisms of Thought. Basic Books, New York (1995)
Holyoak, K., Thagard, P.: Analogical mapping by constraint satisfaction. CognitiveScience 13, 295–355 (1989)
Hummel, J., Holyoak, K.: Distributed representation of structure: A theory of analogical access and mapping. Psychological Review 104, 427–466 (1997)
Kokinov, B.: A hybrid model of reasoning by analogy. In: Holyoak, K., Barnden, J. (eds.) Advances in connectionist and neural computation theory: Vol. 2. Analogical connections, pp. 247–318. Ablex, Norwood (1994a)
Kokinov, B.: The DUAL cognitive architecture: A hybrid multi-agent approach. In: Proceedings of the Eleventh European Conference of Artificial Intelligence (ECAI-94), John Wiley & Sons, London (1994b)
Kokinov, B., Grinberg, M.: Simulating Context Effects in Problem Solving with AMBR. In: Akman, V., et al. (eds.) CONTEXT 2001. LNCS (LNAI), vol. 2116, Springer, Heidelberg (2001)
Kokinov, B., Petrov, A.: Dynamic Extension of Episode Representation in Analogy-Making in AMBR. In: Proceedings of the 22nd Annual Conference of the Cognitive Science Society, Erlbaum, Hillsdale (2000)
Kokinov, B., Petrov, A.: Integration of Memory and Reasoning in Analogy-Making: The AMBR Model. In: Gentner, D., Holyoak, K., Kokinov, B. (eds.) The Analogical Mind: Perspectives from Cognitive Science, MIT Press, Cambridge (2001)
Petrov, A., Kokinov, B.: Processing symbols at variable speed in DUAL: Connectionist activation as power supply. In: Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence (IJCAI-99), pp. 846–851. Morgan Kaufmann, San Francisco (1999)
Pomerleau, D.: ALVINN: An Autonomous Land Vehicle. In a Neural Network. In: Advances in Neural Information Processing Systems 1, Morgan Kaufmann, San Francisco (1989)
Stolzmann, W.: Anticipatory classifier systems. In: Genetic Programming 1998: Proceedings of the Third Annual Conference, pp. 658–664 (1998)
Sutton, R.S.: Integrated architectures for learning, planning, and reacting based on approximating dynamic programming. In: Proceeding of the Seventh International Conference on Machine Learning, pp. 216–224. Morgan Kaufmann, San Mateo (1990)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Petkov, G., Naydenov, T., Grinberg, M., Kokinov, B. (2007). Building Robots with Analogy-Based Anticipation. In: Freksa, C., Kohlhase, M., Schill, K. (eds) KI 2006: Advances in Artificial Intelligence. KI 2006. Lecture Notes in Computer Science(), vol 4314. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69912-5_7
Download citation
DOI: https://doi.org/10.1007/978-3-540-69912-5_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69911-8
Online ISBN: 978-3-540-69912-5
eBook Packages: Computer ScienceComputer Science (R0)