About Some Problems of Designing of Autonomous Robots
DOI:
https://doi.org/10.22213/2413-1172-2017-4-114-116Keywords:
autonomous robot, stochastic matrix, neural network, automorphism, pragmaticsAbstract
The main methods of designing autonomous robots are briefly analyzed, including the automaton model, the classification automaton, the training with reinforcement based on the directional model, the homeostatic method for controlling the behavior of the robot. Deficiencies of methods that do not allow creating an autonomous robot operating in real time mode are identified. Some important works for the topic in the field of cognitive research and biochemistry are mentioned. The lack of a common point of view on the human thought process is shown. It is suggested to consider the autonomous robot and the environment of its work as a text in the language of mathematics. The concept of considering a robot on the basis of pragmatic and semantic analysis as part of semiotic analysis has been advanced. The main postulates of this approach are put forward. The four-level structure of the analysis of automorphisms for the decision making by the robot is formulated.References
Der R., Pantzer T. Emergent robot behavior from the principle of homeokinesis. Technical report, Universität Leipzig, Institut für Informatik, 1999. 256 p.
Verwer S., Eyraud R., Higuera C. PAutomaC: a probabilistic automata and hidden Markov models learning competition. Mach. Learn. 96, 1-2 (July 2014), pp. 129-154.
Fatès N. Stochastic Cellular Automata Solutions to the Density Classification Problem: When Randomness Helps Computing. Theory of Computing Systems; New York, vol. 53, iss. 2 (Aug 2013), pp. 223-242.
Kober J., Bagnell J., Peters J. Reinforcement learning in robotics: A survey. The International Journal of Robotics Research, 32(11), 2013, pp. 1238-1274.
Bostrom N. Superintelligence: Paths, Dangers, Strategies. OUP Oxford, 2016, 432 p.
Kuniaki N., Hiroaki Ar., Yuki S., Tetsuya Og. Multimodal integration learning of robot behavior using deep neural networks. Robot. Auton. Syst. 62, 6 (June 2014), pp. 721-736.
Orsinia C. A., Moorman D. E,. Young J. W., Setlow B., Floresco S. B. Neural mechanisms regulating different forms of risk-related decision-making: Insights from animal models. Neuroscience & Biobehavioral Reviews, vol. 58, 2015, pp. 147-167.
Slioussar N., Kireev M. V., Chernigovskaya T. V., Kataeva G. V., Korotkov A. D., Medvedev S. V. An ER-fMRI study of Russian inflectional morphology. Brain Lang, vol. 130, 2014, pp.33-41. DOI: 10.1016/ j.bandl.2014.01.006.
Chesler A. T., Szczot M., Bharucha-Goebel D. and others. The Role of PIEZO2 in Human Mechanosensation N Engl J Med, vol. 375, pp.1355-1364, October 6, 2016. DOI: 10.1056/NEJMoa1602812.
Ложкин А., Дюкина Н. Структурирование аналитической геометрии на основе симметрий. Saarbrucken: LAP Lambert Academic Publishing, 2012. 176 с.
Ложкин А. Г. Симметрия как единое свойство пространства и живого организма // Тиетта. 2010. № 3(13). С. 23-32.
Lozhkin A., Shubin V., Suslov Y., Bimakov E. In the issue of robots design. Proceedings of the 2017 IEEE Russia Section Young Researchers in Electrical and Electronic Engineering ElConRus 2017, 3 February 2017, pp. 930-933.
