Intelligent pattern recognition system of mobile robot based on stereovision

Intelligent pattern recognition system of mobile robot based on stereovision

Sergey V. Ulyanov
Doctor of Physical and Mathematical Sciences, Dubna State University, Institute of the System Analysis and Management, Professor, 19, Universitetskaya ul., Dubna, Moscow region, 141980, Russia. tel.: +7(49621)66010, This email address is being protected from spambots. You need JavaScript enabled to view it.

Andrey G. Reshetnikov
PhD in Technical Sciences, Dubna State University, Institute of the System Analysis and Management, Assistant Professor, 19, Universitetskaya ul., Dubna, Moscow region, 141980, Russia, tel.: +7(49621)66010, This email address is being protected from spambots. You need JavaScript enabled to view it.

Kirill V. Koshelev
Dubna State University, Institute of the System Analysis and Management, Postgraduate Student, 19, Universitetskaya ul., Dubna, Moscow region, 141980, Russia, tel.: +7(977)710-41-40, This email address is being protected from spambots. You need JavaScript enabled to view it.

Received 01 August 2019

Abstract
Recent advances in digital technology, artificial intelligence and deep machine learning make it possible to resolve problem situations that were previously considered algorithmically unsolvable. The convolutional neural network is a widespread and effective tool for deep learning, with the help of which computer vision problems are successfully solved. The process of classifying images of a convolutional neural network is close to a similar process occurring in the cortex of the human brain. This article discusses the architecture of convolutional neural networks and its application in intelligent robotics. Advantages of convolutional networks are used for recognition with a high degree of invariance to transformations, distortions and scaling. This paper presents a brief description of the modernization of the pattern recognition system based on stereo vision technology. As a result a software recognition module based on a convolutional neural network is presented. An improvement in the quality of recognition through the application of a neural network approach is achieved. The possible consolidation of suggested approach based on quantum soft computing and quantum deep machine learning with quantum neural network IT is discussed.

Key words
Pattern recognition, stereovision, convolutional neural network, training with teacher, convolution operation, classification.

DOI

https://doi.org/10.31776/RTCJ.7307 

Bibliographic description
Ulyanov, S., Reshetnikov, A. and Koshelev, K. (2019). Intelligent pattern recognition system of mobile robot based on stereovision. Robotics and Technical Cybernetics, 7(3), pp.224-232.

UDC identifier:
004.932

References

  1. Ulyanov, S., Reshetnikov, A. and Koshelev, K. (2016). Razrabotka sistemy raspoznavaniya obrazov dlya mobilnogo robota [Development of an image recognition system for a mobile robot]. [online] Sistemnyj analiz v nauke i obrazovanii: jelektron. nauch. zhurnal [Journal of Systems Analysis in Science and Education], no.4. Available at: http://sanse.ru/download/273 [Accessed 1 Aug. 2019]. (in Russian).
  2. Ulyanov, S., Reshetnikov, A. and Koshelev, K. (2018). Ispol'zovanije technologii stereozreniya v sisteme navigatsii mobil'nogo robota [Using stereo vision technology in a mobile robot navigation system]. [online] Programmnije produkti, sistemi i algoritmi: jelektron. nauch. zhurnal [Software Journal: Theory and Applications], no. 2. Available at: http://swsys-web.ru/using-stereo-vision-technology-in-the-navigation-system-of-the-mobile-robot.html [Accessed 1 Aug. 2019]. (in Russian).
  3. Ulyanov, S., Yamafuji, K., Gradetsky, V. and Pagni, A. (1995). Expert Fuzzy-Neuro Controller Design for Wall Climbing Robot for Decontamination of Nuclear-Power Station. Journal of Robotics and Mechatronics, 7(1), pp.75-85.
  4. Ulyanov, S., Yamafuji, K. and Fukuda, T. (1995). Development of intelligent mobile robots for service use and mobile automation systems including wall climbing robots: Pt. 1: Fundamen-tal design principles and motion models. Intern. J. of Intelligent Mechatronics, 1(3), pp.111-143.
  5. Tanaka, T., Ohwi, J., Litvintseva, L., Yamafuji, K. and Ulyanov, S. (1996). Intelligent Control of a Mobile Robot for Service Use in Office Buildings and Its Soft Computing Algorithms. Journal of Robotics and Mechatronics, 8(6), pp.538-554.
  6. Ulyanov, S. (2019). Quantum Fast Algorithm Computational Intelligence PT I SW HW Smart Toolkit. Artificial Intelligence Advances, 1(1).
  7. LeCun, Y., Boser, B., Denker, J., Henderson, D., Howard, R., Hubbard, W. and Jackel, L. (1989). Backpropagation Applied to Handwritten Zip Code Recognition. Neural Computation, 1(4), pp.541-551.
  8. Nemkov, R. (2015). Razrabotka nejrosetevikh algoritmov invariantnogo raspoznavaniya obrazov [Development of neural network algorithms for invariant pattern recognition]. Candidate of Technical Sciences. Stavropol'. (in Russian).
  9. Ranzato, M., Huang, F., Boureau, Y. and LeCun, Y. (2007). Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition. 2007 IEEE Conference on Computer Vision and Pattern Recognition.
  10. Shevel'ov, I. (2010). Nejroni-detektory zritel'noj kory [Visual Cortex Neuron Detectors]. Moscow, p.183. (in Russian).
  11. Haykin, S. (2008). Nejronnije seti: polnij kurs [Neural networks: full course]. Moscow, pp.113, 281-330. (in Russian).
  12. Gonzalez, R. (2012). Tsifrovaya obrabotka izobrazhenij [Digital image processing]. Moscow, p.1104. (in Russian).
  13. Sutton, R. (2011). Obuchenije s podkreplenijem [Reinforcement training]. Moscow, p.399. (in Russian).
  14. Ackley, D., Hinton, G. and Sejnowski, T. (1985). A Learning Algorithm for Boltzmann Machines. Cognitive Science, 9(1), pp.147-169.
  15. Bengio, Y. (2009). Learning Deep Architectures for AI. Foundations and Trends® in Machine Learning, 2(1), pp.1-127.
  16. Ciresan, D., Meier, U. and Schmidhuber, J. (2012). Multi-column deep neural networks for image classification. 2012 IEEE Conference on Computer Vision and Pattern Recognition.
  17. Jarrett, K., Kavukcuoglu, K., Ranzato, M. and LeCun, Y. (2009). What is the best multi-stage architecture for object recognition?. 2009 IEEE 12th International Conference on Computer Vision and Pattern Recognition.
  18. Gill, F. (1985). Prakticheskaya optimizatsiya [Practical optimization]. Moscow, p.509. (in Russian).
  19. Izmajlov, A. (2005). Chislennije metody optimizatsii [Numerical optimization methods]. Moscow, p.304. (in Russian).
  20. Tarkhov, D. (2014). Nejrosetevije modeli i algoritmy [Neural network models and algo-rithms]. Moscow, p.352. (in Russian).
  21. Ulyanov, S., Reshetnikov, A. and Ryabov, N. (2018). Deep machine learning and pattern/face recognition based on quantum neural networks and quantum genetic algorithm. In: Distributed Computing And Gridtechnologies In Science And Education - Book of abstract of the 8th International Conference. p.38.
  22. Ulyanov, S. and Petrov, S. (2012). Kvantovoe raspoznavanije lits i kvantovaja visual'naja kriptografija: modeli i algoritmi [Quantum Face Recognition and Quantum Visual Cryptography: Models and Algorithms]. [online] Sistemnyj analiz v nauke i obrazovanii: jelektron. nauch. zhurnal [Journal of Systems Analysis in Science and Education], no.1. Available at: http://http:/www.sanse.ru/archive/23 [Accessed 1 Aug. 2019]. (in Russian).
Editorial office address: 21, Tikhoretsky pr., Saint-Petersburg, Russia, 194064, tel.: +7(812) 552-13-25 e-mail: zheleznyakov@rtc.ru