Article

Article title SOFT NEURO-FUZZY ALGORITHM MOBILE ROBOT CONTROL
Authors M.V. Bobyr, V.S. Titov
Section SECTION IV. NEURAL NETWORK CONTROL ALGORITHMS
Month, Year 10, 2015 @en
Index UDC 004.896; 681.518.
DOI
Abstract A method to control a mobile robot in the labyrinth using soft computering is presented in the paper. The method is unique because soft arithmetic is used in the structure of fuzzy inference. A soft neuro-fuzzy algorithm of the mobile robot control consists of eight steps described. The paper describes a schemes of the mobile robot and two operating regimes. The mobile robot moves along the line if it operates according to the first regime. It is able to find a way out of the labyrinth if it operates according to the second regime. The robot uses ultrasonic and laser sensors for distance calculating. Moreover, special programmer code which helps to calculate the distance is given. A pulse-width modulation is applied to control motors of mobile robots. An electric schema a pulse-width modulation to control the motors is illustrated. Root mean square error defines accuracy of the mentioned above soft neuro-fuzzy algorithm to control a mobile robot. Working ability of the presented soft neuro-fuzzy algorithm is proved by imitation modeling. The present soft algorithm is compared both to the regression model and the hard fuzzy inference. The obtained results clearly show that the author"s method is much better than the other ones. It is possible to minimize RMSE if the sigmoidal membership function, which describes an output parameter of the fuzzy system, is changed. Some additional experiments given in the paper show efficiency of the method to control mobile robot.

Download PDF

Keywords Fuzzy logic; soft computing; RMSE; mobile robot; neuro-fuzzy algorithm.
References 1. Dubois D., Prade H. Soft computing, fuzzy logic, and artificial intelligence, Soft Computing, 1998, No. 2, pp. 7-11.
2. Zadeh L.A. Some reflections on soft computing, granular computing and their roles in the conception, design and utilization of information/intelligent systems, Soft Computting, 1998, No. 2, pp. 23-25.
3. Pegat A. Nechetkoe modelirovanie i upravlenie [Fuzzy modeling and control]: Translation from English. 2nd ed. Moscow: BINOM. Laboratoriya znaniy, 2013, 798 p.
4. Rouzbeh Shad, Arefeh Shad, Mohammad Saadi Mesgari, Hossein Aghamohammadi, Damoon Molaei. Fuzzy topological simulation for deducing in GIS, Applied Geomatics, 2009, No. 12, Vol. 1, Issue 4, pp. 121-129.
5. Takeshi Morishita, Osamu Tojo. Integer inverse kinematics method using fuzzy logic, Intelligent Service Robotics, 2013, Vol. 6, Issue 2, pp. 101-108.
6. Babak Rezaee. Desulfurization process using Takagi–Sugeno–Kang fuzzy modeling, The International Journal of Advanced Manufacturing Technology January, 2010, Vol. 46, Issue 1, pp. 191-197.
7. Finaev V.I., Sinyavskaya E.D., Pushnina I.V. Nechetkaya model' upravleniya temperaturoy v khlebopekarnoy kamere [Fuzzy control model of temperature at the bread baking chamber], Izvestiya YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2015, No. 4 (165), pp. 149-159.
8. Bobyr' M.V., Milostnaya N.A. Analiz ispol'zovaniya myagkikh arifmeticheskikh operatsiy v strukture nechetko-logicheskogo vyvoda [Analysis of the use of soft arithmetic operations in the structure of fuzzy inference], Vestnik komp'yuternykh i informatsionnykh tekhnologiy [Herald of computer and information technologies], 2015, No. 7, pp. 7-14.
9. Bobyr' M.V., Kulabukhov S.A. Defazzifikatsiya vyvoda iz bazy nechetkikh pravil na osnove metoda raznosti ploshchadey [Defuzzification the output of fuzzy rule base based on the method of difference of squares], Vestnik komp'yuternykh i informatsionnykh tekhnologiy [Herald of computer and information technologies], 2015, No. 9 (135), pp. 32-41.
10. Bobyr' M.V. Adaptatsiya sistemy upravleniya mobil'nym robotom na osnove nechetkoy logiki [Adaptation of the control system of mobile robot based on fuzzy logic], Mekhatronika, avtomatizatsiya, upravlenie [Mechatronics, Automation, Control], 2015, Vol. 16, No. 7, pp. 449-455.
11. Bobyr' M.V., Milostnaya N.A. Nechetkaya model' intellektual'noy sistemy upravleniya mobil'nym robotom [The fuzzy model of the intelligent mobile robot control], Problemy mashinostroeniya i avtomatizatsii [Engineering and Automation Problems], 2015, No. 3, pp. 57-67.
12. Bobyr' M.V., Titov V.S., Belomestnaya A.L. Stabilizatsiya teplovogo rezhima v protsesse rezaniya [Stabilization of the thermal conditions of the cutting process], Mekhatronika, avtomatizatsiya, upravlenie [Mechatronics, Automation, Control], 2010, No. 6, pp. 38-41.
13. Bobyr' M.V., Titov V.S. Metod korrektsii parametrov rezhima rezaniya v sistemakh s ChPU [Method of correction of parameters of the cutting conditions in CNC systems], Mekhatronika, avtomatizatsiya, upravlenie [Mechatronics, Automation, Control], 2010, No. 7, pp. 49-53.
14. Emel'yanov S.G., Titov V.S., Bobyr' M.V. Intellektual'nye sistemy na osnove nechetkoy logiki i myagkikh arifmeticheskikh operatsiy: Ucheb. Posobie [Intelligent system based on fuzzy logic and soft arithmetic operations: Textbook]. Moscow: ARGAMAK-MEDIA, 2014, 341 p.
15. Bobyr' M.V., Titov V.S., Nasser A.A. Otsenka chisla iteratsiy pri obuchenii myagkikh nechetkikh sistem [Estimation of the number of iterations when training soft fuzzy systems], Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta [Proceedings of the South-West State University], 2014, No. 3 (54), pp. 30-37.
16. Bobyr' M.V., Titov V.S., Chervyakov L.M. Adaptatsiya slozhnykh sistem upravleniya s uchetom prognozirovaniya vozmozhnykh sostoyaniy [Adaptation of complex control systems taking into account the forecasting of possible States], Avtomatizatsiya. Sovremennye tekhnologii [Automation. Modern Technology], 2012, No. 5, pp. 3-10.
17. Bobyr' M.V., Titov V.S., Milostnaya N.A., Globin P.V. Otsenka dostovernosti pri modelirovanii nechetko-logicheskikh sistem [The reliability of when mo-melirovanie fuzzy logic systems], Promyshlennye ASU i kontrollery [Industrial Automatic Control Systems and Controllers], 2012, No. 7, pp. 32-38.
18. Palani S., Natarajan U., Chellamalai M. On-line prediction of micro-turning multi-response variables by machine vision system using adaptive neuro-fuzzy inference system (ANFIS), Machine Vision and Applications, 2013, Vol. 24, Issue 1, pp. 19-32.
19. Nihal Erginel. Modeling and analysis of packing properties through a fuzzy inference system, Journal of Intelligent Manufacturing, 2010, Vol. 21, Issue 6, pp. 869-874.
20. Sutapa Chaudhuri, Anirban Middey. Adaptive neuro-fuzzy inference system to forecast peak gust speed during thunderstorms, Meteorology and Atmospheric Physics, 2011, Vol. 114, Issue 3-4, pp. 139-149.
21. Muzzioli S., De B. Baets A comparative assessment of different fuzzy regression methods for volatility forecasting, Fuzzy Optimization and Decision Making, 2013, Vol. 12, Issue 4, pp. 433-450.
22. Karakus M., Tutmez B. Fuzzy and multiple regression modelling for evaluation of intact rock strength based on point load, schmidt hammer and sonic velocity, Rock mechanics and rock engineering, 2006, Vol. 39, No. 1, pp. 45-57.
23. Bobyr' M.V., Emel'yanov S.G., Milostnaya N.A. O nekotorykh svoystvakh modelirovaniya adaptivnykh neyro-nechetkikh sistem na osnove uproshchennogo nechetko-logicheskogo vyvoda [On some properties of the modeling adaptive neuro-fuzzy systems based on simplified fuzzy inference], Informatsionno-izmeritel'nye i upravlyayushchie sistemy [Informationmeasuring and Control Systems], 2014, Vol. 12, No. 5, pp. 4-12.
24. Escaсo J.M., Bordons C., Vilas C., Garcнa M.R., Alonso A.A. Neurofuzzy model based predictive control for thermal batch processes, Journal of Process Control, 2009, Vol. 19, Issue 9, pp. 1566-1575.
25. Firat M., Gungor M. River flow estimation using adaptive neuro fuzzy inference system, River flow estimation using adaptive neuro fuzzy inference system, 2007, Vol. 75, Issues 3–4, pp. 87-96.
26. Bobyr' M.V. Vliyanie chisla pravil na obuchenie nechetko-logicheskoy sistemy [the influence of the number of rules for training of the fuzzy logic system], Vestnik komp'yuternykh i informatsionnykh tekhnologiy [Herald of Computer and Information Technologies], 2014, No. 11 (125), pp. 28-35.
27. Titov V.S., Bobyr' M.V., Milostnaya N.A. ASU prognozirovaniem tochnosti obrabotki detaley [ACS prediction precision machining parts], Avtomatizatsiya v promyshlennosti [Automation in Industry], 2008, No. 4, pp. 3-4.
28. Titov B.C., Bobyr' M.V., Milostnaya N.A. Operatsionnye sistemy real'nogo vremeni dlya sistem ChPU [Operating systems real-time CNC systems], Promyshlennye ASU i kontrollery [Industrial Automatic Control Systems and Controllers], 2008, No. 7, pp. 31-33.
29. Bobyr' M.V. Sposob i ustroystvo upravleniya skorost'yu rezaniya na tokarnom oborudovanii s ChPU [A method and apparatus control the cutting speed in lathe equipment CNC]. Patent RF, No. 2465115, 2010.
30. Titov V.S., Bobyr' M.V., Milostnaya N.A. Ustroystvo prognozirovaniya na oborudovanii s ChPU kachestva obrabotannykh poverkhnostey detail [The device of forecasting on equipment research Institute of CNC quality machined surfaces of the part]. Patent RF, No. 2325247, 2005.

Comments are closed.