Abstract
Direct kinematics (DK) is one of the most challenging problem for cable-driven parallel robot (CDPR) with sagging cables. Solving the DK in real-time is not an issue provided that a guess of the solution is available. But difficulties arise when all DK solutions have to be determined (e.g. in the design phase of the CDPR). Continuation and interval analysis have been proposed to find the solutions but they are computer intensive. A preliminary investigation on the use of classical neural networks (NN) for the DK has shown that they were performing poorly. We present in this paper several methodological improvements that allows to get on average 99.95% of the exact DK solutions in about 5 s. Still this result is not completely satisfactory and we present possible axis to obtain better results in terms of exact results and multiple solutions.
Partly supported by ANR-18-CE10-0004 and ANR-19-P3IA-0002 grants.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Continuation basically amount to incrementally increase the continuation parameter(s) and to use the Newton method to compute the new solution at each step. But the amount of increase in the parameter(s) must be carefully selected to avoid skipping to another Newton solution.
References
Achili, R., et al.: A stable adaptive force/position controller for a C5 parallel robot: a neural network approach. Robotica 30(7), 1177–1187 (2012)
Ahouee, R., Moussavi, S., Hamedi, J.: Neuro-fuzzy intelligent control algorithm for cable-driven robots with elastic cables. In: 2nd International Conference on Cybernetics, Robotics and Control (2017)
Allgower, E.: Numerical Continuation Methods. Springer-Verlag, Berlin (1990)
Azar, W., Akbarimajd, A., Parvari, E.: Intelligent control method of a 6-DOF parallel robot used for rehabilitation treatment in lower limbs. Automatika 57(2), 466–476 (2016)
Boudreau, R., Levesque, G., Darenfed, S.: Parallel manipulator kinematics learning using holographic neural network models. Robot. Comput.-Integr. Manufact. 14(1), 37–44 (1998)
Chawla, I., et al.: Neural network-based inverse kineto-static analysis of cable-driven parallel robot considering cable mass and elasticity. In: 5th International Conference on Cable-Driven Parallel Robots (CableCon). virtual, 7–9 July 2021
Dehghani, M., et al.: Neural network solutions for forward kinematics problem of HEXA parallel robot. In: American Control Conference. Washington, 11–13 June 2008
Geng, Z., Haynes, L.: Neural network for the forward kinematics problem of a Stewart platform. In: IEEE International Conference on Robotics and Automation, pp. 2650–2655. Sacramento, 11-14 April 1991)
Ghasemimi, A., Eghtesad, M., Farid, M.: Neural network solution for forward kinematics problem of cable robots. J. Intell. Robot. Syst. 60, 201–215 (2010)
Haykin, S.: Neural Networks: A Comprehensive Foundation. Prentice Hall PTR, Hoboken (1994)
Irvine, H.M.: Cable Structures. MIT Press, Cambridge (1981)
Kang, R., et al.: Learning the forward kinematics behavior of a hybrid robot employing artificial neural networks. Robotica 30(5), 847–855 (2012)
Lamaury, J., Gouttefarde, M.: Control of a large redundantly actuated cable-suspended parallel robot. In: IEEE International Conference on Robotics and Automation. Karlsruhe, 6–10 May 2013
Li, T., Li, Q., Payendeh, S.: NN-based solution of forward kinematics of 3DOF parallel spherical manipulator. In: IEEE International Conference on Intelligent Robots and Systems (IROS). Edmonton, 2–6 August 2005
Merlet, J.P.: Data base for the direct kinematics of cable-driven parallel robot (CDPR) with sagging cables. Technical report, INRIA (2021). https://hal.inria.fr/hal-03540335v2
Merlet, J.P.: Computing cross-sections of the workspace of suspended cable-driven parallel robot with sagging cables having tension limitations. In: IEEE International Conference on Intelligent Robots and Systems (IROS). Madrid, 1–5 October 2018. https://hal.inria.fr/hal-01965229v1
Merlet, J.P.: Preliminaries of a new approach for the direct kinematics of suspended cable-driven parallel robot with deformable cables. In: Eucomes. Nantes, 20–23 September 2016. https://hal.inria.fr/hal-01419700v1
Merlet, J.P.: The forward kinematics of cable-driven parallel robots with sagging cables. In: 2nd International Conference on cable-driven parallel robots (CableCon), pp. 3–16. Duisburg, 24–27 August 2014. http://www-sop.inria.fr/coprin/PDF/merlet_cablecon2014.pdf
Riehl, N., et al.: Effects of non-negligible cable mass on the static behavior of large workspace cable-driven parallel mechanisms. In: IEEE International Conference on Robotics and Automation, pp. 2193–2198. Kobe, 14–16 May 2009
Yee, C., Lim, K.: Forward kinematics solution of Stewart platform using neural network. Neurocomputing 16(4), 333–349 (1997)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Merlet, JP. (2023). Advances in the Use of Neural Network for Solving the Direct Kinematics of CDPR with Sagging Cables. In: Caro, S., Pott, A., Bruckmann, T. (eds) Cable-Driven Parallel Robots. CableCon 2023. Mechanisms and Machine Science, vol 132. Springer, Cham. https://doi.org/10.1007/978-3-031-32322-5_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-32322-5_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-32321-8
Online ISBN: 978-3-031-32322-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)