Neural Network Learning Algorithms for High-Precision Position Control and Drift Attenuation in Robotic Manipulators
Source abstract
Abstract
In this paper, different learning methods based on Artificial Neural Networks (ANNs) are examined to replace the default speed controller for high-precision position control and drift attenuation in robotic manipulators. ANN learning methods including Levenberg–Marquardt and Bayesian Regression are implemented and compared using a UR5 robot with six degrees of freedom to improve trajectory tracking and minimize position error. Extensive simulation and experimental tests on the identification and control of the robot by means of the neural network controllers yield comparable results with respect to the classical controller, showing the feasibility of the proposed approach.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Iterative Learning Control Systems · Adaptive Control of Nonlinear Systems · Advanced Control Systems Design
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Electrical Engineering, Bialystok University of Technology, Wiejska 45D, 15-351 Bialystok, Poland
Institut Supérieur des Sciences Appliquées et de Technologie Mahdia, Rejiche Road, Mahdia 5121, Tunisia
Polytechnic Department of Engineering and Architecture, University of Udine, 33100 Udine, Italy
References (28)
Show source-provided references
1. Performance analysis of two-degree of freedom fractional order PID controllers for robotic manipulator with payload10.1016/j.isatra.2015.03.013 ↗
2. A genetic algorithm approach to a neural-network-based inverse kinematics solution of robotic manipulators based on error minimization10.1016/j.ins.2012.07.051 ↗
3. A new artificial neural network approach in solving inverse kinematics of robotic arm (denso vp6242)10.1155/2016/5720163 ↗
4. A comparative study of soft computing methods to solve inverse kinematics prob-lem10.1016/j.asej.2017.08.001 ↗
5. Varedi-Koulaei, S.M., and Mokhtari, M. (2018, January 23–25). Trajectory Tracking Solution of a Robotic Arm Based on Optimized ANN. Proceedings of the 2018 6th RSI International Conference on Robotics and Mechatronics, Tehran, Iran.10.1109/ICRoM.2018.8657567 ↗
6. Visual servoing application for inverse kinematics of robotic arm using artificial neural net-works10.24846/v27i2y201806 ↗
7. A Neural Network Controller for Trajectory Control of Industrial Robot Manipulators10.4304/jcp.3.8.1-8 ↗
8. Real Time Control Application of the Robotic Arm Using Neural Network Based Inverse Kinematics Solution
9. Deif, S., Tawfik, M., and Kamal, H.A. (2011, January 24–26). Optimal Tuning of a PD Controller for a Single-Link Flexible Robot Arm Using Adaptive Genetic Algorithm. Proceedings of the 14th International Conference on Aerospace Sciences and Aviation Technology (ASAT-14), Cairo, Egypt.10.21608/asat.2011.23261 ↗
10. Neural network based inverse kinematics solution for trajectory tracking of a robotic arm10.1016/j.protcy.2013.12.451 ↗
11. Fuzzy self-adaptive radial basis function neural network-based control of a seven-link redundant industrial manipulator10.1163/156855301750095569 ↗
12. Jiang, Z.H., and Ishida, T. (2007, January 7–10). Trajectory tracking control of industrial robot manipulators using a neural network controller. Proceedings of the 2007 IEEE International Conference on Systems, Man and Cybernetics, Montreal, QC, Canada.
13. Lima, T.L.d.V., de Freitas, I.S., Filho, J.B.d.M., Sobrinho, C.A.O.N., and da Silva, J.F. (2011, January 6–8). Development and neural control of a robotic manipulator with two degrees of freedom. Proceedings of the Electrodynamic and Mechatronic Systems, Opole, Poland.
14. Adaptive PID control of multi-DOF industrial robot based on neural network10.1007/s12652-020-01693-w ↗
15. Neural Network Control of Multi fingered Robot Hands Using Visual Feedback10.1109/TNN.2008.2012127 ↗
16. Global adaptive tracking control of robot manipulators using neural networks with finite-time learning convergence10.1007/s12555-016-0515-7 ↗
17. Robust adaptive sliding mode control for industrial robot manipulator using fuzzy wavelet neural networks10.1007/s12555-016-0371-5 ↗
18. Lv, Y.F., Huang, Y.B., Wu, X.L., and Jian, L. (2021, January 22–24). Neural Network Tracking Controls of SCARA Manipulator System. Proceedings of the 33rd Chinese Control and Decision Conference (CCDC 2021), Kunming, China.10.1109/CCDC52312.2021.9602275 ↗
19. Neural network robust control of a 3-DOF hydraulic manipulator with asymp-totic tracking10.1002/asjc.2867 ↗
20. Neural Network Model-Based Control for Manipulator: An Autoencoder Perspective10.1109/TNNLS.2021.3109953 ↗
21. Analytic Deep Neural Network-Based Robot Control10.1109/TMECH.2022.3175903 ↗
22. Universal Robots (2023, August 30). User Manual, Ver. 1.6, UR5 with CB2, US ver. Available online: https://www.universal-robots.com/download/manuals-cb-series/user/ur5/16/user-manual-ur5-cb-series-sw16-english-us/.
23. Kebria, P.M., Al-Wais, S., Abdi, H., and Nahavandi, S. (2016, January 9–12). Kinematic and dynamic modelling of UR5 manipulator. Proceedings of the 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Budapest, Hungary.10.1109/SMC.2016.7844896 ↗
24. A comparison of Jacobian-based methods of inverse kinematics for serial robot manipulators10.2478/amcs-2013-0028 ↗
25. (2021, May 31). URScript manual (n.d.). URScript Manual. Available online: https://s3-eu-west-1.amazonaws.com/ur-supportsite/32554/scriptManual-3.5.4.pdf.
26. Modified Levenberg-Marquardt Method for Neural Networks Training
27. de la Cruz, R., Padilla, O., Valle, M.A., and Ruz, G.A. (2021). Modeling Recidivism through Bayesian Regression Models and Deep Neu-ral Networks. Mathematics, 9.10.3390/math9060639 ↗
28. Enhancing fluency and productivity in human-robot collaboration through online scaling of dynamic safety zones10.1007/s00170-022-09781-1 ↗