SIMULATION MODEL OF RECOGNITION AND UNDERSTANDING OF STATIC OBJECTS BY A SELF-LEARNING ROBOT BASED ON MULTI-AGENT NEUROCOGNITIVE ARCHITECTURES

  • I.A. Pshenokova Institute of Computer Science and Problems of Regional Management of KBSC of the Russian Academy of Sciences
  • O.V. Nagoeva Institute of Computer Science and Problems of Regional Management of KBSC of the Russian Academy of Sciences
  • Z.A. Sundukov nstitute of Computer Science and Problems of Regional Management of KBSC of the Russian Academy of Sciences
Keywords: Self-learning robot, multi-agent systems, neurocognitive architecture, simulation model, pattern recognition

Abstract

The purpose of this study is to develop a simulation model based on multi-agent neurocogni-tive systems, which will create an effective tool for solving the problems of recognition and under-standing by the robot of unstructured input data flows. The task is to develop a simulation model of the recognition function of static objects shown on the camera. The presented simulation model of recognition and understanding of static objects by a self-learning robot on the basis of multi-agent neurocognitive architectures allows to create concepts and categories using multimodal flows of input information and interaction with users to expand the system of these concepts and categories and clarify the relationship between them. On this basis, the problems of formalization of the semantics of natural language for linguistic complexes limited by the subject area can be solved, which will allow the use of a dialogue system to solve the problem of setting complex mis-sions to robots. Formalization of semantics of "common sense" on the basis of self-organization of multi-agent neurocognitive architectures will allow to develop simulation models of understanding of natural language statements. This, in turn, will remove the restriction on the creation of a dia-logue system that allows operators using a natural language description to form the formulation of the problem and the statement of its essential conditions.

References

1. Тарасов В.Б. От многоагентных систем к интеллектуальным организациям: философия, психология, информатика. – М.: Эдиториал УРСС, 2002. – 352 с.
2. Рассел С., Норвиг П. Искусственный интеллект. Современный подход. – 2-е изд. – Изд. дом "Вильямс", 2006. – 1408 с.
3. Wooldridge M. An Introduction to MultiAgent Systems Second Edition. – Wiley, 2009. – 484 p. – ISBN: 0470519460.
4. Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence / ed. by G. Weiss. – The MIT Press, 1999. – 643 p. – ISBN: 0262232030.
5. Shoham Y., LeytonBrown K. Multiagent Systems: Algorithmic, GameTheoretic, and Logical Foundations. – Cambridge University Press, 2008. – 504 p. – ISBN: 05.
6. Lesser V.R. and Erman L.D. Distributed interpretation: a model and experiment // IEEE Trans. Computers. – 1980. – Vol. 29 (12). – P. 1144-1163.
7. Xewitt C. Viewing Control Structures as Patterns of Message Passing // Artificial Intelligence. – 1977. – Vol. 8, No. 3. – P. 323-364.
8. Lenat D. BEINGS: Knowledge as Interacting Experts // Proc. of the 1975 IJCAI Conference. – 1975. – P. 126-133.
9. Smith R.G. The Contract Net Protocol: High Level Communication and Control in a Distributed Problem Solver // IEEE Transactions on Computers. – 1980. – Vol. 29, No. 12. – P. 1104-111.
10. Rzevski G. Modelling large complex systems using multi-agent technology // In Proc. of 13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking, and Parallel/Distributed Computing (SNPD2012), August 8-10, Kyoto, Japan, 2012. – P. 434-437.
11. Chen Yao et al. Multi-agent systems with dynamical topologies: Consensus and applications // IEEE circuits and systems magazine. –2013. – Vol. 13, No. 3. – P. 21-34.
12. Chen M., Athanasiadis D., Al Faiya B., McArthur S., Kockar I., Lu H. & De Leon F. Design of a multi-agent system for distributed voltage regulation //19th International Conference on Intelli-gent Systems Application to Power Systems (ISAP), 19 Oct 2017. Piscataway, NJ.: IEEE. – 6 p.
13. Granichin Oleg, Khantuleva Tatjana, Amelina Natalia. Adaptation of Aircraft’s Wings Ele-ments in Turbulent Flows by Local Voting Protocol // IFAC Proceedings. – 2017.
14. Городецкий В.И., Карсаев О.В., Самойлов В.В., Серебряков С.В. Прикладные много-агентные системы группового управления // Искусственный интеллект и принятие ре-шений. – 2009. – № 2.
15. Nagoev Z.V. Multiagent recursive cognitive architecture // Biologically Inspired Cognitive Architectures 2012, Proceedings of the third annual meeting of the BICA Society, in Advances in Intelligent Systems and Computing series. – Springer, 2012. – P. 247-248.
16. Нагоев З.В. Интеллектика, или мышление в живых и искусственных системах. – Наль-чик: Изд-во КБНЦ РАН, 2013. – 211 с.
17. Анохин П.К. Системный анализ интегративной деятельности нейрона // Успехи физиол. наук. – 1974. – Т. 5, № 2. – С. 5-92.
18. Нагоев З.В. Мультиагентные экзистенциальные отображения и функции // Известия КБНЦ РАН. – 2013. – № 4 (54). – С. 64-71.
19. Ivanov P., Nagoev Z., Pshenokova I., Tokmakova D. Forming the Multi-Modal Situation Con-text in Ambient Intelligence Systems on the Basis of Self-Organizing Cognitive Architectures // 5th World Congress on Information and Communication Technologies (WICT), 14-16 De-cember, Morocco. – 2015.
20. Nagoev Z., Nagoeva O., Tokmakova D. System Essence of Intelligence and Multi-agent Exis-tential Mappings // 15th International Conference on Hybrid Intelligent Systems (HIS 2015), Seoul, South Korea, Springer International Publishing Switzerland 2016, A. Abraham et al. (eds.), Hybrid Intelligent Systems, Advances in Intelligent Systems and Computing. 420. – 2016. – P. 67-76. – DOI 10.1007/978-3-319-27221-4_6.
21. Nagoev Z., Gurtueva I., Lutikova L. Model of automatic speech recognition using multi-agent recursive cognitive architecture // Biologically Inspired Cognitive Architectures 2018, Meeting of the BICA Society. – Springer, 2018. – P. 156-163.
Published
2019-05-07
Issue
No 1 (2019)
Section
SECTION I. PROSPECTS OF APPLICATION OF ROBOTIC SYSTEMS