The MGLAIR Multimodal Cognitive Agent Architecture

Summary

The MGLAIR (Multimodal Grounded Layered Architecture with Integrated Reasoning) cognitive agent architecture extends the GLAIR architecture to include a model of concurrent multimodal perception and action. Some existing GLAIR agents use multiple modalities that are implemented ad hoc, lacking integration with, and support from, the architecture itself. MGLAIR provides modalities as instantiable objects within the system, each with its own properties that govern its use and integration with reasoning and acting. By dividing agents' capabilities into modular modalities, MGLAIR allows agents to sense and act simultaneously using different resources with minimal interference, and to consciously decide which resources to focus on for a particular tasks. The resulting agents are more useful than any possible counterparts that can be implemented without such modalities, and provide more realistic models of the capabilities of cognitive agents observed in nature.

Dissertation Proposal

SNePS Research Group Cognitive/Embodied Agents

Papers

  • Jonathan P. Bona and Stuart C. Shapiro. Modality in the MGLAIR Architecture. In Antonio Chella, Roberto Pirrone, Rosario Sorbello and Kamilla Rún Jóhannsdóttir, Eds., Biologically Inspired Cognitive Architectures 2012: Proceedings of the Third Annual Meeting of the BICA Society, Springer, Berlin, 2013, 75-81.
  • Stuart C. Shapiro and Jonathan P. Bona, The GLAIR Cognitive Architecture, International Journal of Machine Consciousness 2,, 2 (2010), 307-332. DOI: 10.1142/S1793843010000515
  • Stuart C. Shapiro and Jonathan P. Bona, The GLAIR Cognitive Architecture. In Alexei Samsonovich, Ed., Biologically Inspired Cognitive Architectures-II: Papers from the AAAI Fall Symposium, Technical Report FS-09-01, AAAI Press, Menlo Park, CA, 2009, 141-152.
  • Josephine Anstey, A. Patrice Seyed, Sarah Bay-Cheng, Dave Pape, Stuart C. Shapiro, Jonathan Bona, and Stephen Hibit The Agent Takes The Stage, International Journal of Arts and Technology (IJART) 2, 4 (2009), 277-296. DOI: 10.1504/IJART.2009.

Technical Reports

  • Jonathan P. Bona and Stuart C. Shapiro, Creating SNePS/Greenfoot Agents and Worlds, SNeRG Technical Note 46, Department of Computer Science and Engineering, University at Buffalo, The State University of New York, Buffalo, NY, May 3, 2001.
  • Jonathan Bona and Michael Prentice, PyRovio: Python API for WowWee Rovio, Department of Computer Science and Engineering, University at Buffalo, May, 2009.






Jonathan P. Bona
Department of Computer Science and Engineering
University at Buffalo, The State University of New York