Multimodal Training Between Agents

  • Matthias Rehm
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2792)


In the system Locator, agents are treated as individual and autonomous subjects that are able to adapt to heterogenous user groups. Applying multimodal information from their surroundings (visual and linguistic), they acquire the necessary concepts for a successful interaction. This approach has proven successful in a domain that exhibits a remarkable variety of possible (often language-specific) structurings: the spatial domain. In this paper, the further development is described (Locator \(^{\rm {\sc 2}}\)) that allows for agent-agent interactions such that an agent is instructed by another agent that plays the role of a teacher.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Andre, E., Rist, T.: Presenting through Performing. In: Lieberman, H. (ed.) Proceedings of IUI 2000, pp. 1–8 (2000)Google Scholar
  2. 2.
    Billard, A., Hayes, G.: DRAMA, a Connectionist Architecture for Control and Learning in Autonomous Robots. Adaptive Behavior 7(1), 35–63 (1999)CrossRefGoogle Scholar
  3. 3.
    Bowerman, M., Levinson, S.C. (eds.): Language acquisition and conceptual development. Cambridge University Press, Cambridge (2001)Google Scholar
  4. 4.
    Cablitz, G.H.: The Acquisition of an Absolute System: Learning to talk about SPACE in Marquesan. In: Proc. of the 31st SCLR Forum (2002)Google Scholar
  5. 5.
    Dautenhahn, K.: The Art of Designing Socially Intelligent Agents. Applied Artificial Intelligence (1998)Google Scholar
  6. 6.
    Cassell, J., et al.: Designing embodied conversational agents. In: Cassell, J., et al. (eds.) Embodied conversational agents, pp. 29–63. MIT Press, Cambridge (2000)Google Scholar
  7. 7.
    Rist, T., et al.: CrossTalk: An Interactive Installation with Animated Presentation Agents. In: Andre, E., et al. (eds.) Proc. of COSIGN 2002, pp. 61–67 (2002)Google Scholar
  8. 8.
    Levinson, S.C.: Frames of Reference and Molyneux’s Question. In: Bloom, P., et al. (eds.) Language and Space, pp. 109–169. MIT Press, Cambridge (1996)Google Scholar
  9. 9.
    Steels, L.: Perceptually grounded meaning creation. In: Tokoro, M. (ed.) Proc. of the Int. Conf. on Multi-Agent Systems, pp. 338–344. AAAI Press, Menlo Park (1996)Google Scholar
  10. 10.
    Steels, L., Kaplan, F.: Bootstrapping Grounded Word Semantics. In: Briscoe, T. (ed.) Linguistic evolution through language acquisition, CUP, Cambridge (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Matthias Rehm
    • 1
  1. 1.Multimedia Concepts and Applications, Institute of Computer ScienceUniversity of AugburgAugsburgGermany

Personalised recommendations