Abstract
Sigma is a nascent cognitive architecture/system that combines concepts from graphical models with traditional symbolic architectures. Here an initial Sigma-based virtual human (VH) is introduced that combines probabilistic reasoning, rule-based decision-making, Theory of Mind, Simultaneous Localization and Mapping and reinforcement learning in a unified manner. This non-modular unification of diverse cognitive, robotic and VH capabilities provides an important first step towards fully adaptive and interactive VHs in Sigma.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
As explained later, what the VH actually does is to model itself as if it were a different VH.
- 2.
The details of this recognition process are beyond the scope of this paper but there are a variety of behavioral cues (e.g. posture changes while concealing an item, gait changes under stress etc.) that could be revealing. Exhibiting and detecting such cues is one of a number of intriguing future directions for this work.
References
Chen, J., Demski, A., Han, T., Morency, L.P., Pynadath, D.V., Rafidi, N., Rosenbloom, P.S.: Fusing symbolic and decision-theoretic problem solving + perception in a graphical cognitive architecture. In: Biologically Inspired Cognitive Architectures (2011)
Grisetti, G., Kummerle, R., Stachniss, C., Burgard, W.: A tutorial on graph-based SLAM. Intell. Transp. Syst. Mag. IEEE 2(4), 31–43 (2010)
Koller, D., Friedman, N.: Principles and Techniques: Probabilistic Graphical Models. MIT Press, Cambridge (2009)
Kopp, S., Krenn, B., Marsella, S.C., Marshall, A.N., Pelachaud, C., Pirker, H., Thórisson, K.R., Vilhjálmsson, H.H.: Towards a common framework for multimodal generation: the behavior markup language. In: Gratch, J., Young, M., Aylett, R.S., Ballin, D., Olivier, P. (eds.) IVA 2006. LNCS (LNAI), vol. 4133, pp. 205–217. Springer, Heidelberg (2006)
Kschischang, F.R., Frey, B.J., Loeliger, H.A.: Factor graphs and the sum-product algorithm. IEEE Trans. Inf. Theor. 47(2), 498–519 (2001)
Laird, J.E.: The Soar Cognitive Architecture. MIT Press, Cambridge (2012)
Langley, P., Laird, J.E., Rogers, S.: Cognitive architectures: research issues and challenges. Cogn. Syst. Res. 10, 141–160 (2009)
Pynadath, D.V., Marsella, S.C.: PsychSim: modeling theory of mind with decision-theoretic agents. In: IJCAI (2005)
Pynadath, D.V., Rosenbloom, P.S., Marsella, S.C.: Reinforcement learning for adaptive theory of mind in the sigma cognitive architecture. In: Goertzel, B., Orseau, L., Snaider, J. (eds.) AGI 2014. LNCS, vol. 8598, pp. 143–154. Springer, Heidelberg (2014)
Rosenbloom, P.S.: Bridging dichotomies in cognitive architectures for virtual humans. In: Proceedings of the AAAI Fall Symposium on Advances in Cognitive Systems (2011)
Rosenbloom, P.S.: Deconstructing reinforcement learning in sigma. In: Bach, J., Goertzel, B., Iklé, M. (eds.) AGI 2012. LNCS, vol. 7716, pp. 262–271. Springer, Heidelberg (2012)
Rosenbloom, P.S.: Towards a 50 ms cognitive cycle in a graphical architecture. In: Proceedings of the 11th International Conference on Cognitive Modeling (2012)
Rosenbloom, P.S.: The sigma cognitive architecture and system. AISB Q. 136, 4–13 (2013)
Rosenbloom, P.S., Demski, A., Han, T., Ustun, V.: Learning via gradient descent in Sigma. In: Proceedings of the 12th International Conference on Cognitive Modeling (2013)
Shapiro, A.: Building a character animation system. In: Allbeck, J.M., Faloutsos, P. (eds.) MIG 2011. LNCS, vol. 7060, pp. 98–109. Springer, Heidelberg (2011)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Swartout, W.: Lessons learned from virtual humans. AI Mag. 31(1), 9–20 (2010)
Ustun, V., Yilmaz, L., Smith, J.S.: A conceptual model for agent-based simulation of physical security systems. In: Proceedings of the 44th Annual Southeast Regional Conference. ACM (2006)
Whiten, A. (ed.): Natural Theories of Mind. Basil Blackwell, Oxford (1991)
Acknowledgments
This effort has been sponsored by the Office of Naval Research and the U.S. Army. Statements and opinions expressed do not necessarily reflect the position or the policy of the United States Government, and no official endorsement should be inferred. We would also like to thank Ari Shapiro for his overall support with SmartBody.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Ustun, V., Rosenbloom, P.S. (2015). Towards Adaptive, Interactive Virtual Humans in Sigma. In: Brinkman, WP., Broekens, J., Heylen, D. (eds) Intelligent Virtual Agents. IVA 2015. Lecture Notes in Computer Science(), vol 9238. Springer, Cham. https://doi.org/10.1007/978-3-319-21996-7_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-21996-7_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-21995-0
Online ISBN: 978-3-319-21996-7
eBook Packages: Computer ScienceComputer Science (R0)