A.I. Panov Formation of an Image Component of Knowledge of the Cognitive Agent with a Sign-based Model of Worldview
A.I. Panov Formation of an Image Component of Knowledge of the Cognitive Agent with a Sign-based Model of Worldview


In the theory of the sign-based model of worldview the elementary unit of information (at modeling of any cognitive processes, such as planning, goal-setting and reflection) is the four-component structure named sign. Sign components are responsible for implementing relatively simple involuntary processes that play the role of automatic or supporting functions. To describe the supporting functions of the signbased world model, the concepts of the causal matrix and the causal network are used, the definitions of which are specified in this paper. The procedures of activity spreading on the causal network are introduced. With a focus on the image component of the sign, the paper proposes an algorithm for the formation of the causal matrix and a fragment of the causal network. As an example, the problem of identification of anomalies in human locomotory movements is considered.


sign, sign-based world model, cognitive function, HTM, causal matrix, causal network, activity spreading.

PP. 84-96.

DOI 10.14357/20718632180409


1. Osipov G.S. et al. Znakovaya kartina mira sub"ekta povedeniya [Sign-based model of Actor’s Worldview]. M.: Fizmatlit, 2018. 264 p. (In Russian).
2. Osipov G.S., Panov A.I. Relationships and operations in agent’s sign-based model of the world // Sci. Tech. Inf. Process. 2018. Vol. 45, № 5. P. 1–14.
3. Karpov V.E. A sign-oriented mobile robot-control system // Sci. Tech. Inf. Process. 2018. Vol. 45, № 5-6, pp. 281-288.
4. Semiotics and Intelligent Systems Development / ed. Gudwin R., Queiroz J. IGI Global, 2007. 368 p.
5. Kulinich A.A. A model of agents (robots) command behavior: The cognitive approach // Automation and Remote Control. 2016. Vol. 77, № 3. P. 510-522.
6. Osipov G.S., Panov A.I., Chudova N. V. Behavior control as a function of consciousness. I. World model and goal setting // J. Comput. Syst. Sci. Int. 2014. Vol. 53, № 4. P. 517–529.
7. Vinogradov, A.N., Zhilyakova, L.Yu., Osipov, G.S. Dynamic intelligent systems: I. Knowledge representation and basic algorithms// Journal of Computer and Systems Sciences International. 2002. Vol. 41, № 6. P. 953–960.
8. Osipov G.S., Panov A.I., Chudova N. V. Behavior Control as a Function of Consciousness. II. Synthesis of a Behavior Plan // J. Comput. Syst. Sci. Int. 2015. Vol. 54, № 6. P. 882–896.
9. Kiselev G.A., Panov A.I. Sign-based Approach to the Task of Role Distribution in the Coalition of Cognitive Agents // SPIIRAS Proc. 2018. № 57. P. 161–187.
10. Panov A.I. Behavior Planning of Intelligent Agent with Sign World Model // Biol. Inspired Cogn. Archit. 2017. Vol. 19. P. 21–31.
11. Panov A.I. Algebraic Properties fo Recogniton Operators in Modeling Visual Perception of Dynamic Scenes // Proceedings of the International Conference IIP-10. 2014. P. 133.
12. Osipov G.S. Formulation of subject domain models: Part I. heterogeneous semantic nets// Soviet journal of computer and systems sciences. 1992. Vol. 30, № 2. P. 1–12.
13. Velichkovskij B.M. Geterarhiya kognitivnoj organizacii: proshloe, nastoyashchee i budushchee [Heterarchy of cognitive organization: past, present and future] // V knige: Sed'maya mezhdunarodnaya konferenciya po kognitivnoj nauke Tezisy dokladov. Otvetstvennye redaktory: Yu. I. Aleksandrov, K. V. Anohin. 2016. P. 194. (In Russian).
14. Kiselev G., Kovalev A., Panov A.I. Spatial reasoning and planning in sign-based world model // Artificial Intelligence / ed. Kuznetsov S., Osipov G.S., Stefanuk V. Springer International Publishing, 2018. P. 1–10.
15. Ermek A., Kiselev G., Panov A.I. Task and Spatial Planning by the Cognitive Agent with Human-like Knowledge Representation // Interactive Collaborative Robotics / ed. Ronzhin A., Rigoll G., Meshcheryakov R. Springer International Publishing, 2018. P. 1-12.
16. Kuznecova Yu.M. et al. Yazykovaya sistema kak regulyator planirovaniya povedeniya kognitivnyh agentov [Linguistic system as a regulator of behavior planning of cognitive agents] // Vos'maya mezhdunarodnaya konferenciya po kognitivnoj nauke: Tezisy dokladov. 2018. (In press) (In Russian).
17. George D., Hawkins J. Towards a mathematical theory of cortical micro-circuits // PLoS Comput. Biol. 2009. Vol. 5, № 10. P. e1000532.
18. Hawkins J., Ahmad S., Cui Y. A Theory of How Columns in the Neocortex Enable Learning the Structure of the World //Front. Neural Circuits. 2017. Vol. 11. P. 1–18.
19. Panov A.I., Skrynnik A. Automatic formation of the structure of abstract machines in hierarchical reinforcement learning with state clustering // ICML\IJCAI Work. Plan. Learn. 2018.
20. Finn V.K. On the definition of empirical regularities by the JSM method for the automatic generation of hypotheses // Sci. Tech. Inf. Process. 2012. Vol. 49, № 5. P. 261–267.
21. Suzuki N. et al. Learning motion patterns and anomaly detection by human trajectory analysis //Systems, Man and Cybernetics, 2007. ISIC. IEEE International Conference on. – IEEE, 2007. – С. 498-503.
22. Kratz L., Nishino K. Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models //Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on. – IEEE, 2009. – С. 1446-1453.
23. Li W., Mahadevan V., Vasconcelos N. Anomaly detection and localization in crowded scenes //IEEE transactions on pattern analysis and machine intelligence. – 2014. – Т. 36. – №. 1. – С. 18-32.
24. Ren L. et al. A data-driven approach to quantifying natural human motion //ACM Transactions on Graphics (TOG). – ACM, 2005. – Т. 24. – №. 3. – С. 1090-1097.
25. Bütepage J. et al. Deep representation learning for human motion prediction and classification //IEEE Conference on Computer Vision and Pattern Recognition (CVPR). – 2017. – С. 2017.
26. Du Y., Wang W., Wang L. Hierarchical recurrent neural network for skeleton based action recognition //Proceedings of the IEEE conference on computer vision and pattern recognition. – 2015. – С. 1110-1118.
27. CMU Graphics Lab. Carnegie Mellon University Motion Capture Database. 2003. url: http://
28. Daylidyonok I., Frolenkova A., Panov A.I. Extended Hierarchical Temporal Memory for Motion Anomaly Detection // Biologically Inspired Cognitive Architectures 2018 / ed. Samsonovich A. V. Springer International Publishing, 2018. P. 69–81.

2024 / 01
2023 / 04
2023 / 03
2023 / 02

© ФИЦ ИУ РАН 2008-2018. Создание сайта "РосИнтернет технологии".