Abstract
Underlying the importance of communication in highly distributed and autonomous systems, i.e., multi-agent systems, such communication should be autonomously managed by the system itself. As such, it should be managed on the individual level of each individual agent, and still result in a general consistent framework of communication. Such an approach, opposite to the centralised and controlled stance, poses additional problems and introduces new challenges for the system design. It is therefore crucial to design and develop agents that could cope with this new tasks and be able to emerge, align and maintain a common framework of communication. This research intends to fill the current gap and investigate the dynamics of the model of individual semiosis, i.e., narrowing the interaction pattern of Language Game Model to a case of a single teaching agent. In particular, the presented research studies both, analytically and using a simulated framework, the dynamics of the alignment process itself, depending on the internal behaviour of the agent, and the dynamics of the observed phase transition in the alignment process in case of deviations from common context settings.
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
Bloom, P.: How children learn the meanings of words. The MIT Press (2002)
Blythe, R.A., Smith, K., Smith, A.D.M.: Learning Times for Large Lexicons Through Cross-Situational Learning. Cognitive Science 34(4), 620–642 (2010)
DeBeule, J., DeVylder, B., Belpaeme, T.: A cross-situational learning algorithm for damping homonymy in the guessing game. In: Proceedings of ALIFE X. MIT Press (2006)
Droeschel, D., Stckler, J., Holz, D., Behnke, S.: Towards Joint Attention for a Domestic Service Robot Person Awareness and Gesture Recognition using Time-of-Flight Cameras. In: Proc. of the IEEE Int. Conference on Robotics and Automation (ICRA), Shanghai, China, pp. 1205–1210 (2011)
Harnad, S.: The symbol grounding problem. Physica D: Nonlinear Phenomena 42(1-3), 335–346 (1990)
Ito, M., Tani, J.: Joint attention between a humanoid robot and users in imitation game. In: Proc. of the 3rd Int. Conf. on Development and Learning (ICDL 2004), La Jolla, U.S.A. (2004)
Kaplan, F., Hafner, V.: The Challenges of Joint Attention. Interaction Studies 7, 67–74 (2004)
Lakoff, G., Johnson, M.: Philosoph in the Flesh: the Embodied Mind and its Challenge to Western Thought. Basic Books (1999)
Lorkiewicz, W., Katarzyniak, R.P.: Representing the Meaning of Symbols in Autonomous Agents. In: Intelligent Information and Database Systems, pp. 183–189. IEEE (2009)
Lorkiewicz, W., Kowalczyk, R., Katarzyniak, R., Vo, B.: On Topic Selection Strategies in Multi-Agent Naming Game. In: AAMAS 2011, pp. 499–506 (2011)
Lorkiewicz, W., Katarzyniak, R., Kowalczyk, R.: Deviating from Common Context in Individual Semiosis in Multi-Agent Systems. In: Wang, Y., Li, T. (eds.) ISKE2011. AISC, vol. 122, pp. 229–238. Springer, Heidelberg (2011)
Rosch, E., Mervis, C., Gray, W., Johnson, D., Boyes-Braem, P.: Basic objects in natural categories. Cogn. Psychol. 8, 382–439 (1976)
Saussure, F.: Course in General Linguistics. Open Court Pub. Co. (1986)
De Silva, P.R.S., Tadano, K., Lambacher, S.G., Herath, S.: Unsupervised approach to acquire robot joint attention. In: Proc. of the 4th International Conference on Autonomous Robots and Agents, pp. 601–606. IEEE (2009)
Siskind, J.M.: A computational study of cross-situational techniques for learning word-to-meaning mappings. Cognition 61(1-2), 39–91 (1996)
Smith, K., Smith, A.D.M., Blythe, R.A., Vogt, P.: Cross-Situational Learning: A Mathematical Approach. In: Vogt, P., Sugita, Y., Tuci, E., Nehaniv, C.L. (eds.) EELC 2006. LNCS (LNAI), vol. 4211, pp. 31–44. Springer, Heidelberg (2006)
Smith, L., Yu, C.: Infants rapidly learn word-referent mappings via cross-situational statistics. Cognition 106, 1558–1568 (2008)
Smith, K., Smith, A.D.M., Blythe, R.A.: Cross-Situational Learning: An Experimental Study of Word-Learning Mechanisms. Cognitive Science 35, 480–498 (2011)
Steels, L.: Language as a Complex Adaptive System. In: Schoenauer, M., Deb, K., Rudolph, G., Yao, X., Lutton, E., Merelo, J.J., Schwefel, H.-P. (eds.) PPSN VI. LNCS, pp. 17–26. Springer, Heidelberg (2000)
Steels, L.: Language Games for Autonomous Robots. IEEE Intelligent Systems (2001)
Steels, L.: The Naming Game. The Electricity Journal 11(9), 30–33 (2004)
Steels, L.: Modeling the Formation of Language in Embodied Agents: Methods and Open Challenges. In: Evolution of Communication and Language in Embodied Agents, pp. 223–233. Springer, Heidelberg (2010)
Quine, W.V.O.: Word and Object. MIT Press, Cambridge, MA (1960)
Vogt, P.: The emergence of compositional structures in perceptually grounded language games. Artificial Intelligence 167(1-2), 206–242 (2005)
Vogt, P.: The physical symbol grounding problem. Cognitive Systems Research 3(3), 429–457 (2002)
Yu, C., Smith, L.B.: Rapid Word Learning under Uncertainty via Cross-Situational Statistics. Psychological Science 18, 414–420 (2007)
Yurovsky, D., Yu, C.: Mutual Exclusivity in Cross-Situational Statistical Learning. In: Love, B.C., McRae, K., Sloutsky, V.M. (eds.) Proceedings of the 30th Annual Conference of the Cognitive Science Society, pp. 715–720. Cognitive Science Society, Austin (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Lorkiewicz, W., Katarzyniak, R., Kowalczyk, R. (2012). Individual Semiosis in Multi-Agent Systems. In: Nguyen, N.T. (eds) Transactions on Computational Collective Intelligence VII. Lecture Notes in Computer Science, vol 7270. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-32066-8_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-32066-8_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-32065-1
Online ISBN: 978-3-642-32066-8
eBook Packages: Computer ScienceComputer Science (R0)