Abstract
Quadruped robot leg calibration has great significance in improving positioning accuracy. However, the traditional calibration method is to manually measure the actual joint angles using protractors, which is time-consuming and inconvenient. To improve the calibration efficiency and accuracy, this paper presents an online intelligent kinematic calibration method for quadruped robots based on machine vision and deep learning. The proposed method contains three parts: detect the marker fixed on the robot leg using machine vision methods, transform coordinates into the reference coordinate system by camera internal and external parameters calibration, calculate joint angles and compensate errors by deep-learning-based inverse kinematics. The experimental validation result shows that the proposed intelligent method can significantly improve the calibration speed with an acceptable accuracy compared to the manual calibration method.
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
References
Smisek, J., Jancosek, M., Pajdla, T.: 3D with Kinect . In: 2011 IEEE International Conference on Computer Vision Workshops, pp. 3–25 (2013)
Horaud, R., Dornaika, F.: Hand-eye calibration. Int. J. Robot. Res. 14(3), 195–210 (1995). https://doi.org/10.1177/027836499501400301
Sreenivas, T., Subhash, K.: Inverse kinematics in robotics using neural networks. Inf. Sci. 116, 147–164 (1999)
Xu, Q., et al.: SuperMeshing: a new deep learning architecture for increasing the mesh density of physical fields in metal forming numerical simulation . J. Appl. Mech. 89, 1–11 (2002)
Jiang, H., Nie, Z., Yeo, R., Farimani, A.B., Kara, L.B.: StressGAN: a generative deep learning model for two-dimensional stress distribution prediction . J. Appl. Mech. 88(5), 051005 (2021)
Nie, Z., Lin, T., Jiang, H., Kara, L.B.: Topologygan: topology optimization using generative adversarial networks based on physical fields over the initial domain . J. Mech. Des. 143(3), 031715(2021)
Pfaff, T., Fortunato, M., Sanchez-Gonzalez, A., et al.: Learning mesh-based simulation with graph networks. arXiv preprint arXiv:201003409 (2020)
Xie, Y., Franz, E., Chu, M., et al.: tempogan: a temporally coherent, volumetric GAM for super-resolution fluid flow. ACM Trans. Graph. (TOG) 37(4), 1–15 (2018)
Klaus, H., Strobl, G.H.: Optimal hand-eye calibration. In: 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems (2006)
NøRGård, P.M., Ravn, O., Poulsen, N.K., et al.: Neural Networks for Modelling and Control of Dynamic Systems-A Practitioner’s Handbook, Springer, London (2000)
Bayramoglu, E., Andersen, N.A., Ravn, O., et al.: Pre-trained neural networks used for non-linear state estimation. In: Proceedings of the 2011 10th International Conference on Machine Learning and Applications and Workshops. IEEE (2011)
Hasan, A.T., Ismail, N., Hamouda, A.M.S., et al.: Artificial neural network-based kinematics Jacobian solution for serial manipulator passing through singular configurations. Adv. Eng. Softw. 41(2), 359–67 (2010)
Acknowledgement
This work is supported by National Natural Science Foundation of China under Grant 52175237, and National Key R&D Program of China under Grant 2019YFA0706701.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, H. et al. (2021). An Online Intelligent Kinematic Calibration Method for Quadruped Robots Based on Machine Vision and Deep Learning. In: Liu, XJ., Nie, Z., Yu, J., Xie, F., Song, R. (eds) Intelligent Robotics and Applications. ICIRA 2021. Lecture Notes in Computer Science(), vol 13016. Springer, Cham. https://doi.org/10.1007/978-3-030-89092-6_31
Download citation
DOI: https://doi.org/10.1007/978-3-030-89092-6_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89091-9
Online ISBN: 978-3-030-89092-6
eBook Packages: Computer ScienceComputer Science (R0)