Support for autonomous navigation of mobile robot based on its internal neural network model

E.Yu. Shmalko, I.V. Prokopiev, A.I. Diveev

Abstract


Autonomous navigation is one of the key tasks in the development of control systems for real autonomous mobile robots. The main source of information about the location of the robot is its sensory system. However, any sensory system has weaknesses. In this regard, there is a need to support the navigation system in some way that does not depend on the readings of the sensors. The paper presents the developed technology for determining the position of a mobile robot in an autonomous mode based on an internal model. The approach involves using on board an exact model of a real robot identified by a neural network. Under the conditions of modern computing power, obtaining such a model is much easier than its analytical derivation. At the same time, the model takes into account various dynamic properties of the model, which are difficult to take into account manually. When identifying, it is proposed to use a mixed approach, when the kinematic part of the robot model is considered known, and the dynamic properties of the model are identified by a neural network. Having a fairly accurate model on board, the robot adjusts its position determined by the sensors in accordance with its position obtained using the neural network model. In case of failures in the operation of the sensors or their disconnection, the robot can continue the autonomous execution of the task for some time. In the experimental part, the problem of autonomous movement of a mobile robot along a given trajectory is considered.

Full Text:

PDF (Russian)

References


Sharp, N., Soliman, Y., Crane, K. (2019). Navigating intrinsic triangulations. ACM Transactions on Graphics (TOG), 38, 1 - 16.

Z. Li and J. Huang, (2018) Study on the use of Q-R codes as landmarks for indoor positioning: Preliminary results,” 2018 IEEE/ION Position, Location and Navigation Symposium (PLANS), pp. 1270-1276, doi: 10.1109/PLANS.2018.8373516.

Novoselov, S., Sychova, O. and Tesliuk, S. (2019). Development of the Method Local Navigation of Mobile Robot a Based on the Tags with QR Code and Wireless Sensor Network, 2019 IEEE XVth International Conference on the Perspective Technologies and Methods in MEMS Design (MEMSTECH), pp. 46-51, doi: 10.1109/MEMSTECH.2019.8817405.

Zhou, C. and Liu, X. (2016) The Study of Applying the AGV Navigation System Based on Two Dimensional Bar Code,” 2016 International Conference on Industrial Informatics - Computing Technology, Intelligent Technology, Industrial Information Integration (ICIICII), pp. 206-209, doi: 10.1109/ICIICII.2016.0057.

Sani, M.F. and Karimian, G. (2017). Automatic navigation and landing of an indoor AR. drone quadrotor using ArUco marker and inertial sensors, 2017 International Conference on Computer and Drone Applications (IConDA), pp. 102-107, doi: 10.1109/ICONDA.2017.8270408.

Marut, A., Wojtowicz, K. and Falkowski, K. (2019) ArUco markers pose estimation in UAV landing aid system, 2019 IEEE 5th International Workshop on Metrology for AeroSpace (MetroAeroSpace), pp. 261-266, doi: 10.1109/MetroAeroSpace.2019.8869572.

Tian, W., Chen, D., Yang, Z. and Yin, H. (2020) The application of navigation technology for the medical assistive devices based on

Aruco recognition technology, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2894-2899, doi: 10.1109/IROS45743.2020.9341231.

Geng, Ke, Chulin, N.A., (2017). UAV Navigation Algorithm Based on Improved Algorithm of Simultaneous Localization and Mapping

with Adaptive Local Range of Observations. Herald of the Bauman Moscow State Technical University. Series Instrument Engineering.

18698/0236-3933-2017-3-76-94.

Dae Hee Won, Sebum Chun, Sangkyung Sung, Taesam Kang and Young Jae Lee (2008) Improving mobile robot navigation performance using vision based SLAM and distributed filters, 2008 International Conference on Control, Automation and Systems, pp. 186-191, doi: 10.1109/ICCAS.2008.4694547.

Cheeseman P., Smith R., Self M. (1987) A stochastic map for uncertain spatial relationships. 4th Int. Symp. on Robotic Research, pp. 467–474.

Lu, F., Milios, E. (1997) Globally Consistent Range Scan Alignment for Environment Mapping. Autonomous Robots,4(4):333-349.

Biswas J., Veloso M. Depth camera based indoor mobile robot localization and navigation. IEEE Int. Conf. on Robotics and Automation, 2012, pp. 1697–1702. DOI: 10.1109/ICRA.2012.6224766

Tu, Y., Huang, Z., Zhang, X., Yu, W., Xu, Y., Chen, B. (2015). The Mobile Robot SLAM Based on Depth and Visual Sensing in Structured Environment. In: Kim, JH., Yang, W., Jo, J., Sincak, P., Myung, H. (eds) Robot Intelligence Technology and Applications 3. Advances in Intelligent Systems and Computing, vol 345. Springer, Cham.

Zeng, R., Kang, Y., Yang, J., Zhang, W. and Wu, Q. (2018). Terrain Parameters Identification of Kinematic and Dynamic Models for a Tracked Mobile Robot, 2018 2nd IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), pp. 575-582, doi: 10.1109/IMCEC.2018.8469223.

Cox, P., Toth, R. (2021) Linear parameter-varying subspace identification: A unified framework Automatica. 123. 109296.

1016/j.automatica.2020.109296.

De Le ́on, C.L.C.-D. et al. (2022). Parameter Identification of a Robot Arm Manipulator Based on a Convolutional Neural Network, IEEE Access, vol. 10, pp. 55002-55019, doi: 10.1109/ACCESS.2022.3177209.

Ge, W., Wang, B. and Mu, H. (2019). Dynamic Parameter Identification for Reconfigurable Robot Using Adaline Neural Network, 2019 IEEE International Conference on Mechatronics and Automation (ICMA), pp. 319-324, doi: 0.1109/ICMA.2019.8816533.

Liu, G.P. (2012). Nonlinear identification and control: a neural network approach. Springer Science & Business Media.

Williams G. et al. (2016) Aggressive driving with model predictive path integral control 2016 IEEE International Conference on Robotics and Automation (ICRA)), p. 1433-1440.

Shmalko, E., Rumyantsev, Y., Baynazarov, R., Yamshanov, K. (2021). Identification of Neural Network Model of Robot to Solve the Optimal Control Problem. Informatics and Automation, 20(6), 1254-1278. https://doi.org/10.15622/ia.20.6.3


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность MoNeTec 2024

ISSN: 2307-8162