Abstract
In this paper, we design a vision-based tactile sensor which can capture the two-dimensional deformation images when stressed. The sensor mainly consists of a transparent elastomer, a \(4 \times 4\) or \(8 \times 8\) array of single layer markers on the surface of the elastomer and a camera which is used to capture the markers. According to Hooke’s law, we propose a scheme using the nonlinear fitting and activation function of neural network with three layers to fit stiffness coefficient of elastomer, then we can calculate the three-dimensional tactile information. Compared to the tactile sensor with two layers having markers of different colors, our method has the advantage of simpler manufacturing process. Besides, it does not need expensive camera and precise focusing process, which is necessary for DFD(Depth from defocus) algorithm to calculate depth displacement information of markers. Further more, our method adapts neural network to fit the stiffness coefficient of elastomer, making the parameters have physical significance, which accords with the physical properties of elastomer. The sensor can reconstruct three-dimensional tactile information in real time with a speed of about 30fps.
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
Chuang, CH., et al.: Flexible tactile sensor for the grasping control of robot fingers. In: 2013 International Conference on Advanced Robotics and Intelligent Systems (ARIS). IEEE (2013)
Ulmen, J., Cutkosky, M.: A robust, low-cost and low-noise artificial skin for human-friendly robots. In: InternationaL Conference on Robotics and Automation (ICRA) (2010)
Hu, X., et al.: A flexible capacitive tactile sensor array with micro structure for robotic application. Sci. Chin. Inf. Sci. 57(12), 1–6 (2014)
Begej, S.: Fingertip-shaped optical tactile sensor for robotic applications. In: Proceedings of IEEE 1988 International Conference on Robotics and Automation, pp. 1752–1757. IEEE (1988)
Ito, Y., Kim, Y., Obinata, G.: Contact region estimation based on a vision-based tactile sensor using a deformable touchpad. Sens. 14(4), 5805–5822 (2014)
Ito, Y., Kim, Y., Obinata, G.: Slippage degree estimation for dexterous handling of vision-based tactile sensor. In: IEEE Sensors 2009, IEEE (2009)
Ito, Y., et al.: Contact state estimation by vision-based tactile sensors for dexterous manipulation with robot hands based on shape-sensing. Int. J. Adv. Robot. Syst 8(4), 225–234 (2011)
Ito, Y., et al.: Vision-based tactile sensing and shape estimation using a fluid-type touchpad. IEEE Trans. Autom. Sci. Eng. 9(4), 734–744 (2012)
Sato, K., et al.: Finger-shaped gelforce: sensor for measuring surface traction fields for robotic hand. IEEE Trans. Haptics 3(1), 37–47 (2010)
Johnson, M.K., Adelson, E.H.: Retrographic sensing for the measurement of surface texture and shape. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009. IEEE (2009)
Guo, F., Zhang, F., et al.: Measurement of Three-Dimensional Deformation and Load Using Vision-based Tactile Sensor
Kamiyama, K., Kajimoto, H., Kawakami, N., et al.: Evaluation of a vision-based tactile sensor. In: Proceedings of 2004 IEEE International Conference on Robotics and Automation 2004, (ICRA 2004), vol. 2, pp. 1542–1547. IEEE (2004)
Sokolnikoff, I.S., Specht, R.D.: Mathematical Theory of Elasticity. McGraw-Hill, New York (1956)
Li, J., Cheng, J., Shi, J., Huang, F.: Brief introduction of Back Propagation (BP) neural network algorithm and Its improvement. In: Jin, D., Lin, S. (eds.) Advances in Computer Science and Information Engineering. AISC, vol. 169, pp. 553–558. Springer, Heidelberg (2012)
Acknowledgment
The work was supported by the National Natural Science Foundation of China (Grant Nos. 91420302, 91520201).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yang, C., Sun, F., Fang, B., Li, L. (2017). A Stable and Efficient Vision-Based Tactile Sensor with Tactile Detection Using Neural Network. In: Sun, F., Liu, H., Hu, D. (eds) Cognitive Systems and Signal Processing. ICCSIP 2016. Communications in Computer and Information Science, vol 710. Springer, Singapore. https://doi.org/10.1007/978-981-10-5230-9_34
Download citation
DOI: https://doi.org/10.1007/978-981-10-5230-9_34
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-5229-3
Online ISBN: 978-981-10-5230-9
eBook Packages: Computer ScienceComputer Science (R0)