Motion control is one of the most intensively developing areas that require a constant development of theory and applications.


Nowadays one of the most topical problems is control of nonlinear multiply connected systems functioning autonomously under the conditions of uncertain parameters and disturbances and at presence of stationary and mobile obstacles. This problem doesn’t have a proper solution yet. The most important level for the operation of autonomous objects is the motion planning level that should ensure setting the intermediary goals and operation of the vehicle in the environment with stationary and mobile obstacles.

So, the application of the described structure in implementation of a position-path control system allows for a comprehensive implementation of the controller level and of a number of functions of the planning level. Besides, the position-path control systems provide an effective coupling of the planner with the controller level.

At present, the researchers are actively developing the modifications of position path control. One of such modifications is an approach based on finding and using biological analogies, particularly using the results of neurophysiological and neuro-cybernetic experiments studying the neural systems of a human and of the animals. However the direct application of the known neurophysiological data for modeling the human psyche doesn’t give any practical results due to extreme complexity of the modeling object – human brain. However the research in this area remains extremely relevant.



Features of Position-Path Control Systems based on Artificial Neural Networks

Application area: intelligent position-path control systems for robotic vehicles operating under the conditions of environmental uncertainty.

Distinctive features: technical imitation of biological systems ensuring “intelligent” behavior in a complicated non-formalized environment; matching the segments of the environment to the reacting elements of the neural network of afferent synthesis. The sought path is generally formed by a physical modeling of the afferent synthesis process on the neural network.

Advantages over other methods: simplicity and clearness, low computational expenditures, capability of dynamic control of vehicle’s motion in real time.


The examples of implementations of position-path control systems based on artificial neural networks


Unmanned boat with autonomous control system under the conditions of multiple above-water obstacles.


Visualization of the artificial neural network formed by the autonomous control system on detection of the obstacle by the computer vision system.



The process of tuning the artificial neural network during stabilization and motion of the robotic helicopter in complicated weather conditions.


1. Pshikhopov, V., Chernukhin, Y., Fedotov, A., Pereversev, V., Krukhmalev, V. Development of intelligent control system for autonomous underwater vehicle // 2014 the 4th International Workshop on Computer Science and Engineering-Winter, WCSE 2014

2. D.A.Beloglazov, V.F. Guzik, E.U. Kosenko, V.A.Krukhmalev, M.U.Medvedev, V.A.Pereverzev, V.Kh.Pshikhopov, A.O.Pyavchenko, R.V.Saprykin, V.V.Soloviev, V.I.Finaev, U.V.Chernukhin, I.O.Shapovalov, Intelligent path planning for environments with mobile obstacles. Ed. V.Kh.Pshikhopov, Moscow, Fizmatlit, 2014, 450p

3. D.A. Beloglazov, A.R. Gaiduk, E.U.Kosenko, M.U.Medvedev, V.Kh.Pshikhopov, V.V.Soloviev, A.E. Titov, V.I. Finaev, I.O.Shapovalov, Group control of mobile obstacles in undetermined environments. Ed. V.Kh.Pshikhopov, Fizmatlit, Moscow, 2015, 305p.

4. V.Kh. Pshikhopov, U.V.Chernukhin, A.A.Fedotov, V.F.Guzik, , M.U.Medvedev, B.V.Gurenko, A.O.Pyavchenko, R.V.Saprykin,. V.A.Pereverzev, A.A.Priemko, Devlopment of intelligent control system for autonomous underwater vehicle // Izvestiya SFEDU.Technical sciences. – 2014. – No 3(152). – pp. 87 – 101.

5. Finaev, V., Kobersy, I., Beloglazov, D., Kosenko, E., Soloviev, V. Design of the neuro-like learning control system for a vehicle. // WSEAS Transactions on Systems and Control, 2015, WSEAS Transactions on Systems and Control 10, pp. 328-334.

6. Beloglazov, D.A., Finaev, V.I. Development of information support aiming at investigation into trainability of hybrid adaptive neuro-fuzzy regulators. // World Applied Sciences Journal, 2013, 23 (11), pp. 1433-1440.

7. Pshikhopov, V., Chernukhin, Y.,Guzik V., Medvedev M., Gurenko B., Piavchenko A., Saprikin R., Pereversev V., Krukhmalev V. Implementation of intelligent control system for autonomous underwater vehicle // Applied mechanics and materials, 2014, p. 704.

8. A.O. Pyavchenko, V.A.Pereverze, A complex method of situational behavior planning for a mobile robotic object under the conditions of partial uncertainty in 2D space. // Izvestiya SFEDU.Technical sciences – 2016. – No. 3(176), p. 97 – 114.