Hostname: page-component-848d4c4894-p2v8j Total loading time: 0.001 Render date: 2024-06-06T16:47:14.326Z Has data issue: false hasContentIssue false
  • English
  • Français

Regulation of cost function weighting matrices in control of WMR using MLP neural networks

Published online by Cambridge University Press:  28 October 2022

Moharam Habibnejad Korayem Open the ORCID record for Moharam Habibnejad Korayem [Opens in a new window] ,
Hamidreza Rezaei Adriani  and
Naeim Yousefi Lademakhi Open the ORCID record for Naeim Yousefi Lademakhi [Opens in a new window]
Moharam Habibnejad Korayem*
Affiliation:
Robotics Research Laboratory, Center of Excellence in Experimental Solid Mechanics and Dynamics, School of Mechanical Engineering, Iran University of Science and Technology, Tehran, Iran
Hamidreza Rezaei Adriani
Affiliation:
Robotics Research Laboratory, Center of Excellence in Experimental Solid Mechanics and Dynamics, School of Mechanical Engineering, Iran University of Science and Technology, Tehran, Iran
Naeim Yousefi Lademakhi
Affiliation:
Robotics Research Laboratory, Center of Excellence in Experimental Solid Mechanics and Dynamics, School of Mechanical Engineering, Iran University of Science and Technology, Tehran, Iran
*
*Corresponding author. E-mail: hkorayem@iust.ac.ir
Get access Rights & Permissions [Opens in a new window]

Abstract

In this paper, a method based on neural networks for intelligently extracting weighting matrices of the optimal controllers’ cost function is presented. Despite the optimal and robust performance of controllers with the cost function, adjusting their gains which are the weighting matrices for the system state variables vector and the system inputs vector, is a challenging and time-consuming task that is usually selected by trial and error method for each specific application; and even little changes in the weighting matrices significantly impact problem-solving and system optimization. Therefore, it is necessary to select these gains automatically to improve controller performance and delete human energy to find the best gains. As a linear controller, linear quadratic regulator, and as a nonlinear controller, nonlinear model predictive control have been employed with trained networks to track the path of a wheeled mobile robot. The simulation and experimental results have been extracted and compared to validate the proposed method. These results have been demonstrated that the intelligent controller’s operation has lower error than the conventional method, which works up to 7% optimal in tracking and up to 19% better in angle state error; furthermore, as the most important aim, the required time and effort to find the weighting matrices in various situations has been omitted.

Keywords

intelligent regulation gainsoptimal controlmulti-layer perceptron neural networks (MLP-NN)wheeled mobile robot (WMR)
Type
Research Article
Information
Robotica , Volume 41 , Issue 2 , February 2023 , pp. 530 - 547
Copyright
© The Author(s), 2022. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Hu, Y., Su, H., Fu, J., Karimi, H. R., Ferrigno, G., De Momi, E. and Knoll, A., “Nonlinear model predictive control for mobile medical robot using neural optimization,” IEEE Trans. Ind. Electron. 68(12), 12636–12645 (2020).CrossRefGoogle Scholar
St-Onge, D., Kaufmann, M., Panerati, J., Ramtoula, B., Cao, Y., Coffey, E. B. and Beltrame, G., “Planetary exploration with robot teams: implementing higher autonomy with swarm intelligence,” IEEE Robot. Autom. Mag. 27(2), 159–168 (2019).CrossRefGoogle Scholar
Vasconez, J. P., Kantor, G. A. and Cheein, F. A. A., “Human-robot interaction in agriculture: a survey and current challenges,” Biosyst. Eng. 179, 35–48 (2019).CrossRefGoogle Scholar
Dönmez, E. and Kocamaz, A. F., “Design of mobile robot control infrastructure based on decision trees and adaptive potential area methods,” Iran. J. Sci. Technol. Trans. Electr. Eng. 44(1), 431–448 (2020).CrossRefGoogle Scholar
Lee, H. and Kim, H. J., “Trajectory tracking control of multirotors from modelling to experiments: a survey,” Int. J. Control Autom. Syst. 15(1), 281–292 (2017).CrossRefGoogle Scholar
Elsisi, M., Mahmoud, K., Lehtonen, M. and Darwish, M. M., “An improved neural network algorithm to efficiently track various trajectories of robot manipulator arms,” IEEE Access 9, 11911–11920 (2021).CrossRefGoogle Scholar
Xin, G., Xin, S., Cebe, O., Pollayil, M. J., Angelini, F., Garabini, M., Vijayakumar, S. and Mistry, M., “Robust footstep planning and LQR control for dynamic quadrupedal locomotion,” IEEE Robot. Autom. Lett. 6(3), 4488–4495 (2021).CrossRefGoogle Scholar
Alalwan, A., Mohamed, T., Chakir, M. and Laleg, T. M., “Extended Kalman filter based linear quadratic regulator control for optical wireless communication alignment,” IEEE Photonics J. 12(6), 1–12 (2020).CrossRefGoogle Scholar
Trimpe, S., Millane, A., Doessegger, S. and D’Andrea, R., “A Self-Tuning LQR Approach Demonstrated on an Inverted Pendulum,” In: IFAC Proceedings, vol. 47 (2014) pp. 11281–11287.Google Scholar
Almobaied, M., Eksin, I. and Guzelkaya, M., “Design of LQR Controller With Big Bang-Big Crunch Optimization Algorithm Based on Time Domain Criteria,” In: 24th Mediterranean Conference on Control and Automation (MED) (IEEE, 2016) pp. 1192–1197.CrossRefGoogle Scholar
Kayacan, E. and Chowdhary, G., “Tracking error learning control for precise mobile robot path tracking in outdoor environment,” J. Intell. Robot. Syst. 95(3), 975–986 (2019).CrossRefGoogle Scholar
Dönmez, E., Kocamaz, A. F. and Dirik, M., “Bi-RRT Path Extraction and Curve Fitting Smooth with Visual Based Configuration Space Mapping,” In: International Artificial Intelligence and Data Processing Symposium (IDAP) (IEEE, 2017) pp. 1–5.CrossRefGoogle Scholar
Innocenti, M., Baralli, F., Salotti, F. and Caiti, A., “Manipulator Path Control using SDRE,” In: Proceedings of the American Control Conference, ACC, IEEE Cat. No. 00CH36334 (2000), pp. 3348–3352.Google Scholar
Korayem, M. H., Irani, M. and Nekoo, S. R., “Load maximization of flexible joint mechanical manipulator using nonlinear optimal controller,” Acta Astronaut. 69(7–8), 458–469 (2011).CrossRefGoogle Scholar
Korayem, M. H., Nekoo, S. R. and Kazemi, S., “Finite-time feedback linearization (FTFL) controller considering optimal gains on mobile mechanical manipulators,” J. Intell. Robot. Syst. 94(3), 727–744 (2019).CrossRefGoogle Scholar
Lee, Y. H., Lee, Y. H., Lee, H., Kang, H., Lee, J. H., Park, J. M., Kim, Y. B., Moon, H., Koo, J. C., Choi, H. R., “Whole-body control and angular momentum regulation using torque sensors for quadrupedal robots,” J. Intell. Robot. Syst. 102(3), 1–15 (2021).CrossRefGoogle Scholar
Korayem, M. H., Shiri, R., Nekoo, S. R. and Fazilati, Z., “Non-singular terminal sliding mode control design for wheeled mobile manipulator,” Ind. Robot. Int. J. 44(4), 501–511 (2017).CrossRefGoogle Scholar
Adriani, H. R., Lademakhi, N. Y. and Korayem, A. H., “Superiority of Nonlinear and Stable MPC in a Differential Mobile Robot: Accuracy and Solving Speed,” In: 9th RSI International Conference on Robotics and Mechatronics (ICRoM) (IEEE, 2021) pp. 13–17.CrossRefGoogle Scholar
Chen, Y., Li, Z., Kong, H. and Ke, F., “Model predictive tracking control of nonholonomic mobile robots with coupled input constraints and unknown dynamics,” IEEE Trans. Ind. Inform. 15(6), 3196–3205 (2018).CrossRefGoogle Scholar
Saputra, R. P., Rakicevic, N., Chappell, D., Wang, K. and Kormushev, P., “Hierarchical decomposed-objective model predictive control for autonomous casualty extraction,” IEEE Access 9, 39656–39679 (2021).CrossRefGoogle Scholar
Fierro, R. and Lewis, F. L., “Control of a nonholonomic mobile robot: backstepping kinematics into dynamics,” J. Robotic Syst. 14(3), 149–163 (1997).3.0.CO;2-R>CrossRefGoogle Scholar
Korayem, M. H. and Shafei, A. M., “Motion equation of nonholonomic wheeled mobile robotic manipulator with revolute-prismatic joints using recursive Gibbs-Appell Formulation,” Appl. Math. Model. 39(5–6), 1701–1716 (2015).CrossRefGoogle Scholar
Dönmez, E., Kocamaz, A. F. and Dirik, M., “A vision-based real-time mobile robot controller design based on gaussian function for indoor environment,” Arab. J. Sci. Eng. 43(12), 7127–7142 (2018).CrossRefGoogle Scholar
Chen, Z., Liu, Y., He, W., Qiao, H. and Ji, H., “Adaptive-neural-network-based trajectory tracking control for a nonholonomic wheeled mobile robot with velocity constraints,” IEEE Trans. Ind. Electron. 68(6), 5057–5067 (2020).CrossRefGoogle Scholar
Peng, G., Chen, C. P. and Yang, C., “Neural networks enhanced optimal admittance control of robot-environment interaction using reinforcement learning,” IEEE Trans. Neural Netw. Learn. Syst. 33(9), 1–11 (2021).CrossRefGoogle Scholar
Nakamura-Zimmerer, T., Gong, Q. and Kang, W., “QRnet: optimal regulator design with LQR-augmented neural networks,” IEEE Cont. Syst. Lett. 5(4), 1303–1308 (2020).CrossRefGoogle Scholar
Yan, Z., Le, X. and Wang, J., “Tube-based robust model predictive control of nonlinear systems via collective neurodynamic optimization,” IEEE Trans. Ind. Electron. 63(7), 4377–4386 (2016).CrossRefGoogle Scholar
Fan, J. and Han, M.. Nonlinear Model Predictive Control of Ball-Plate System Based on Gaussian Particle Swarm Optimization, Congress on Evolutionary Computation (IEEE, 2012) pp. 1–6.Google Scholar
Meadows, E. S. and Rawlings, J. B., “Model Predictive Control,” In: Nonlinear Process Control, Henson, M. A. and Seborg, D. E., Chapter 5 (Prentice-Hall, Englewood Cliffs, NJ, 1997) pp. 233–310.Google Scholar
Wu, X., Xu, M. and Wang, L., “Differential speed steering control for four-wheel independent driving electric vehicle,” IEEE Int. Symp. Ind. Electron. 14, 1–6 (2013).Google Scholar
Sharma, K. R., Dušek, F. and Honc, D., “Comparitive Study of Predictive Controllers for Trajectory Tracking of Non-Holonomic Mobile Robot,” In: 21st International Conference on Process Control (PC) (IEEE, 2017) pp. 197–203.CrossRefGoogle Scholar