Abstract
Cognition does not only depend on bottom-up sensor feature abstraction, but also relies on contextual information being passed top-down. Context is higher level information that helps to predict belief states at lower levels. The main contribution of this paper is to provide a formalisation of perceptual context and its integration into a new process model for cognitive hierarchies. Several simple instantiations of a cognitive hierarchy are used to illustrate the role of context. Notably, we demonstrate the use context in a novel approach to visually track the pose of rigid objects with just a 2D camera.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Both of these examples appear in [16] but are also well-known in the cognitive psychology literature.
- 2.
It is of course intuitive in this simple example that as \({N}_2\) has the benefit of the knowledge of the transition dynamics of the object it can better estimate its position and provide this context to direct the camera.
- 3.
The pose of a rigid object in 3D space has 6\(^\circ \) of freedom, three describing its translated position, and three the rotation or orientation, relative to a reference pose.
References
Albus, J.S., Meystel, A.M.: Engineering of Mind: An Introduction to the Science of Intelligent Systems. Wiley, London (2001). http://eu.wiley.com/WileyCDA/WileyTitle/productCd-0471438545.html
Ashby, W.R.: Design for a Brain. Chapman and Hall, London (1952). https://archive.org/details/designforbrainor00ashb
Bakker, B., Schmidhuber, J.: Hierarchical reinforcement learning based on subgoal discovery and subpolicy specialization. In: Proceedings of the 8-th Conference on Intelligent Autonomous Systems, IAS-8, pp. 438–445 (2004)
Beer, S.: Decision and Control. Wiley, London (1966)
Biederman, I., Kubovy, M., Pomerantz, J.: On the semantics of a glance at a scene. In: Perceptual Organization, pp. 213–263. Lawrence Erlbaum, NJ (1981)
Brooks, R.A.: A robust layered control system for a mobile robot. IEEE J. Robot. Autom. 2(1), 14–23 (1986). https://doi.org/10.1109/JRA.1986.1087032
Cavanagh, P.: What’s up in top-down processing? In: Gorea, A. (ed.) Representations of Vision: Trends and Tacit Assumptions in Vision Research, pp. 295–304. Cambridge University Press, Cambridge (1991)
Clark, K., et al.: A framework for integrating symbolic and sub-symbolic representations. In: 25th Joint Conference on Artificial Intelligence (IJCAI -16) (2016)
Dayan, P., Hinton, G.E.: Feudal reinforcement learning. In: Advances in Neural Information Processing Systems 5 (NIPS) (1992)
Dietterich, T.G.: Hierarchical reinforcement learning with the MAXQ value function decomposition. J. Artif. Intell. Res. (JAIR) 13, 227–303 (2000)
Drescher, G.L.: Made-up Minds: A Constructionist Approach to Artificial Intelligence. MIT Press, Cambridge (1991)
Gilbert, C.D., Li, W.: Top-down influences on visual processing. Nat. Rev. Neurosci. 14(5) (2013). https://doi.org/10.1038/nrn3476
Hawkins, J., Blakeslee, S.: On Intelligence. Times Books, Henry Holt and Company, New York (2004)
Hengst, B., Pagnucco, M., Rajaratnam, D., Sammut, C., Thielscher, M.: Perceptual context in cognitive hierarchies. CoRR abs/1801.02270 (2018). http://arxiv.org/abs/1801.02270
Hubel, D.H., Wiesel, T.N.: Brain mechanisms of vision. In: A Scientific American Book: The Brain, pp. 84–96 (1979)
Johnson, J.: Designing with the Mind in Mind: Simple Guide to Understanding User Interface Design Rules. Morgan Kaufmann Publishers Inc., San Francisco (2010)
Jong, N.K.: Structured exploration for reinforcement learning. Ph.D. thesis, University of Texas at Austin (2010)
Kaelbling, L.P.: Hierarchical learning in stochastic domains: preliminary results. In: Machine Learning Proceedings of the Tenth International Conference. pp. 167–173. Morgan Kaufmann, San Mateo (1993)
Koenig, N., Howard, A.: Design and use paradigms for Gazebo, an open-source multi-robot simulator. In: International Conference on Intelligent Robots and Systems (IROS), pp. 2149–2154. IEEE/RSJ (2004)
Konidaris, G., Kuindersma, S., Grupen, R., Barto, A.: Robot learning from demonstration by constructing skill trees. Int. J. Robot. Res. (2011). https://doi.org/10.1177/0278364911428653
Lepetit, V., Fua, P.: Monocular model-based 3D tracking of rigid objects. Found. Trends. Comput. Graph. Vis. 1(1), 1–89 (2005). https://doi.org/10.1561/0600000001
Marthi, B., Russell, S., Andre, D.: A compact, hierarchical q-function decomposition. In: Proceedings of the Proceedings of the Twenty-Second Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-06), pp. 332–340. AUAI Press, Arlington (2006)
Martin, R.M., Brock, O.: Online interactive perception of articulated objects with multi-level recursive estimation based on task-specific priors. In: IROS, pp. 2494–2501. IEEE (2014)
Minsky, M.: The Society of Mind. Simon & Schuster Inc., New York (1986)
Nilsson, N.J.: Teleo-reactive programs and the triple-tower architecture. Electron. Trans. Artif. Intell. 5, 99–110 (2001)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Francesco (1988). Revised second printing edn
Turchin, V.F.: The Phenomenon of Science. Columbia University Press, New York (1977)
Acknowledgments
The alphabetically last author wants to thank Franz Baader for many years of successful collegial collaboration, in particular within the joint research cluster on Logic-Based Knowledge Representation that was funded by the German Research Foundation (DFG) over many years. This centre would never have come to fruition without Franz’s relentless pursuit of excellence not only in the projects that he was directly involved in but also with the cluster as a whole. One of the most pleasant experiences that we shared during that time was our journey to IJCAI’09 in Pasadena, which I am sure Franz remembers.
This material is based upon work supported by the Asian Office of Aerospace Research and Development (AOARD) under Award No: FA2386-15-1-0005. This research was also supported under Australian Research Council’s (ARC) Discovery Projects funding scheme (project number DP 150103035).
Disclaimer. Any opinions, findings, and conclusions or recommendations expressed in this publication are those of the authors and do not necessarily reflect the views of the AOARD.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Hengst, B., Pagnucco, M., Rajaratnam, D., Sammut, C., Thielscher, M. (2019). Perceptual Context in Cognitive Hierarchies. In: Lutz, C., Sattler, U., Tinelli, C., Turhan, AY., Wolter, F. (eds) Description Logic, Theory Combination, and All That. Lecture Notes in Computer Science(), vol 11560. Springer, Cham. https://doi.org/10.1007/978-3-030-22102-7_16
Download citation
DOI: https://doi.org/10.1007/978-3-030-22102-7_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-22101-0
Online ISBN: 978-3-030-22102-7
eBook Packages: Computer ScienceComputer Science (R0)