Abstract
The accuracy of cable-driven parallel robots (CDPRs) is an important performance criteria in many of their applications. While various modeling and calibration approaches have been proposed to improve the accuracy of CDPRs, only few works in the literature systematically compare the accuracy of different models and approaches in practice. Therefore, this work compares the accuracy improvements achieved by different CDPR and machine-learning (ML) models (linear regression, boosted regression trees, and neural networks) that are optimized or trained based on measurement data from a CDPR. A hyperparameter study is performed to select the most accurate models, which exhibit the least overfitting on a validation dataset. The accuracy of these models is evaluated in practice using an additional test measurement. Optimized CDPR models yield accuracy improvements of up to \(61\%\) on the training and \(30\%\) on the validation dataset. The best ML model achieves improvements of \(66\%\) and \(41\%\), respectively. These results show that suitable optimized CDPR and ML models can significantly improve the accuracy of CDPR in practice.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Akhmetzyanov, A. et al.: Deep learning with transfer learning method for error compensation of cable-driven robot. In: ICINCO (2020)
Chawla, I et al.: Neural network-based inverse kineto-static analysis of cable-driven parallel robot considering cable mass and elasticity. In: Cable-Driven Parallel Robots: Proceedings of the 5th International Conference on Cable-Driven Parallel Robots. pp. 50–62. Springer (2021)
Choi, S.-H., Park, K.-S.: The integrated elasto-plastic cable modeling for cable driven parallel robots (CDPRs). In: 2017 17th International Conference on Control, Automation and Systems (ICCAS). pp. 420–422. IEEE (2017)
Fabritius, M et al.: A framework for analyzing the accuracy, complexity, and long-term performance of cable-driven parallel robot models. In: Mechanism and Machine Theory, vol 185, pp. 105331. (2023) ISSN: 0094-114X
Fabritius, M. et al.: A nullspace-based force correction method to improve the dynamic performance of cable-driven parallel robots. In: Mechanism and Machine Theory, vol 181. pp. 105177. (2023) ISSN: 0094-114X
Leica Absolute Tracker AT960. Accessed: 11 Nov 2023. https://hexagon.com/products/leica-absolute-tracker-at960
Linear Regression. Accessed 11 July 2023. https://scikit-learn.org/ stable/modules/generated/sklearn.linear model.LinearRegression.html
Martin, C. et al.: Accuracy improvement for CDPRs based on direct cable length measurement sensors. In: International Conference on Cable-Driven Parallel Robots. pp. 348–359. Springer (2021)
Miermeister, P.: Model selection and parameter optimization for cable-driven parallel robots. PhD thesis. Stuttgart, Germany, University of Stuttgart (2021)
Mishra, U.A., Caro, S.: Forward kinematics for suspended under-actuated cable-driven parallel robots: a neural network approach. In: International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. vol. 85451, American Society of Mechanical Engineers. V08BT08A053 (2021)
Parikh, P.J., Lam, S.S.: Solving the forward kinematics problem in parallel manipulators using an iterative artificial neural network strategy. Int. J. Adv. Manuf. Technol. 40, 595–606 (2009)
Pott, A.: An Improved force distribution algorithm for over-constrained cable-driven parallel robots. In: Computational Kinematics. vol. 15, pp. 139–146. Springer (2014). ISBN: 978-94-007-7213-7
PyTorch. Accessed 11 July 2023. https://pytorch.org/
Riehl, N.: 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. IEEE (2009)
XGBoost.: Accessed 11 July 2023. https://xgboost.readthedocs.io/en/ stable/python/python api.html#xgboost.train
Zubizarreta, A., et al.: Real time direct kinematic problem computation of the 3PRS robot using neural networks. Neurocomputing 271, 104–114 (2018)
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
Fabritius, M., Kraus, W., Pott, A. (2023). Improving the Accuracy of Cable-Driven Parallel Robots Through Model Optimization and Machine-Learning. In: Okada, M. (eds) Advances in Mechanism and Machine Science. IFToMM WC 2023. Mechanisms and Machine Science, vol 147. Springer, Cham. https://doi.org/10.1007/978-3-031-45705-0_55
Download citation
DOI: https://doi.org/10.1007/978-3-031-45705-0_55
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45704-3
Online ISBN: 978-3-031-45705-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)