Abstract
The electronic skin described in the article comprises screen-printed graphene-based sensors, intended to be used for robotic applications. The precise mathematical model allowing the touch pressure estimation is required during its calibration. The article describes the recurrent neural network model for graphene-based electronic skin calibration, in which parameters are not homogeneous, and the touch force characteristics have visible hysteretic behaviour. The presented method provides a simple alternative to the models known in the literature.
You have full access to this open access chapter, Download conference paper PDF
Keywords
1 Introduction
Skin is the thin layer of tissue forming the natural outer covering of the body. It is a protective barrier against mechanical, thermal and physical injury and hazardous substances. It also acts as a sensory organ (touch, temperature, strain, moisture). The electronic skin (e-skin) and its applications in many domains have attracted researchers worldwide for over three decades [8]. E-skin as an interface that mimics a biological tissue is being developed in medicine (smart health care [18], prosthesis [20]), and robotics [3]). In robotics, it allows for increasing safety in human-machine cooperation, the agility of robotic manipulation [19], and soft robotics [2, 4].
To calibrate and establish the measurement characteristics of e-skin sensors, a standard approach base on the measurement of the force exerted by a reference device. In the known research, linear, quadratic, and cubic polynomial models were fitted to data to calibrate the example sensor [5, 9, 21]. The best results were obtained using a Huber regression with a quadratic polynomial model. In [15] e-skin semi-automatised calibration procedure using industrial robot FANUC LRMate 200iC equipped with a reference force sensor was presented where second-order exponential function and logistic function were used. To assess fitting results, two parameters were analysed: adjusted coefficient of determination (ARS) and root-mean-square error (RMSE). However, in all the abovementioned research [15] the e-skin graphene sensor’s characteristics manifest hysteretic behaviour, and the visible effect of hysteresis on the modelling accuracy has not yet been discussed.
Hysteresis is the dependence of the state of a system on the state’s history, and we can find this phenomenon in many science fields as physics, chemistry, and engineering. Besides the subject-specific models, some hysteretic models capture general features of many systems with hysteresis that can be classified as algebraic models, transcendental models, differential models and integral models [16]. One of the promising solutions is to use artificial neural networks to model the system’s data with hysteretic behaviour. They have distinct advantages over linear identification methods, i.e., the approximation of multivariable nonlinear functions, the simple gradient-based adaptation of model parameters and a rapid calculation of neural network equations. In contrast to analytical models, the design procedure of the ANN does not demand an exact knowledge of model physical equations and physical parameters that describe the model, but only values of model variables in the causal form. Several neural network architectures with recurrent layers and memory capacity were proposed recently, e.g. recurrent neural networks for ultra-capacitors [1], physics-informed deep neural networks for mechanical dampers [10] or extended Preisach neural network [6] among others.
The presented research aims to propose a novel method of e-skin graphene sensor modelling using the NARX recurrent neural network that can describe the hysteretic behaviour of the sensor.
2 Graphene-Based Electronic Skin
The e-skin used for the research consisted of two layers [13, 14]. The first is a conductive layer of comb electrodes printed on plastic foil and connected along columns and rows. In contrast, the second one comprises FSR graphene sensors arranged in a rectangular pattern placed on a plastic foil. In the research, a matrix with the size of a single sensor (approx. 5 \(\times \) 5 mm) was used. The e-skin controller measures the pressure for each sensor and transmits the position and touch force exerted on the active surface. The data is sent to a computer, processed and saved. The computer software enables the visualization of the touch results as a colour-coded image. Figure 1 presents the hand touch measurement for the 16 \(\times \) 32 FSR matrix.
The measurement acquisition setup comprised the FANUC LR Mate 200iC manipulator, the R-30iA Mate manipulator controller, the e-skin with a driver, the OnRobot Hex-e 6-axis force and torque measuring device with a controller, and a general-purpose PC. Data from e-skin sensors and the reference Hex-e sensor were acquired during the calibration procedure. Data acquisition was subdivided into the ‘loading phase’, when the force exerted on the particular sensor of the e-skin by the robotic arm increased, and the ‘unloading phase’, when the force decreased (Fig. 2).
3 Neural-Network Modelling
Nonlinear AutoRegressive eXogenous model (NARX) in the form of the recurrent artificial neural network (R-ANN) was used to model the e-skin graphene sensor to estimate the pressure (force exerted on sensor) based on the sensor readouts. NARX-RNN nonlinear model extends the autoregressive linear model with the exogenous input (ARX), popular in time-series nonlinear modelling. NARX-RNN model is the input-output model, where the output in each step is described by input signal with noise. NARX-RNN has memory capabilities. It memorizes previous data and can be used to model hysteretic behaviour. While making a decision, it considers the current input and what it has learned from the inputs it received previously. Output from the previous step is fed as input to the current step creating a feedback loop.
In such a case, the nonlinear part of the NARX-RNN model was described as
where \(y_{\text {NN}}(k)\) - output of the NARX-RNN, \(F_{\text {NN}}(k)\) - estimated output (touch pressure) at step k, V(k) - sensor readouts at the step k, k - sample number, \(t=kT_{p}\) - time, \(T_p\) - sampling time.
Exemplary scheme of used in the research NARX-RNN model is presented in Fig. 3.
The NARX-RNN comprises the nonlinear hidden layer that processes the input data as
where \(y^{(1)}{ }_{(j) \text {NL}}(k)\) - output signal of the j-th neuron in the nonlinear layer, \(x^{(1)}{ }_{(j)\text {NL}}(k)\) - input signal to the j-th neuron in the nonlinear layer, n - the number of neurons in the nonlinear layer, p - the number of neuron inputs in the nonlinear layer, \(w^{(1)}{ }_{i, j}\) - the weight of the i-th input to j th neuron in the nonlinear layer, \(x_i(k)\) - i-th input to the network (with tapped delay line, D inputs in Fig. 3), \(b_{(n)}^{(1)}\) - the threshold offset of the n-th neuron in the nonlinear layer. The second term of (2) describes the recurrent feedback loop with delay (D in Fig. 3). In the considered case, the output of the RNN network \(y^{(1)}{ }_\text {L}(k)\) is the output signal from a linear output layer, with 1 linear neuron described as follows
where \(y_{\text {NN}}(k)\) - the network output, equal to the linear layer output, \(x^{(2)}_{\text {L}}(k)\) - the input signal to the neuron in the linear output layer, \(w_{\left( \text {L}\right) i, 1}^{(2)}\) - the weight of the ith input to neuron in the linear output layer, and \(b_{\text {L}}{ }^{(2)}\) - the neuron’s bias in the linear output layer.
For the training and evaluation of the NARX-RNN model, the estimation error was calculated as follows
4 Results
4.1 Research Method
The Mean Squared Error (MSE) has been used to describe the performance function \(E_{\text {NARX-RNN}}\) of the NARX-RNN model during training and testing. The changes in the weights in the i-th iteration were used in the NARX-RNN models according to the Levenberg-Marquardt algorithm, and variable metrics method [12]. The training algorithm stop conditions were defined because of the possible large step of each iteration. The mentioned conditions are usually estimated as the assumed minimum value of the performance function and the maximum number of training iterations. In the case described in this article, the stopping conditions were: epochs \(=1000\), \(E_{\text {NARX-RNN}} \le 10^{-6}\). The early stop method was used during training of the NARX-RNN model in a controlled way by segmentation of the dataset into three subsets namely: Training subset used during NARX-RNN training (70% of data), Validation subset used for NARX-RNN validation during training and to prevent the data overfitting (15% of data), Testing subset not used in the training phase, only used for comparison of the models during final evaluation (15% of data). The NARX-RNN models were trained per iteration in batch mode [7], while weights and biases were initialized using the Nguyen- Widrow initialization procedure [17]. The values of the sensor readouts and the touch pressure measured by the HEX device were normalized to the range [0, 1] to avoid the early stop due to neuron saturation. The quality of the NARX-RNN model of the e-skin graphene sensor was evaluated based on the MSE performance function, and the goodness of fit between the estimated data and the reference data was calculated as Root Mean Square Error (RMSE) [11].
4.2 Modelling
The proposed NARX-RNN model was evaluated on the exemplary sensor (row 6 and column 16 of the sensor matrix). The sensor-measured characteristic is presented in Fig. 4. The two types of nonlinear hidden layer neuron transfer functions were used: hyperbolic tangent sigmoid transfer function (tansig) and symmetric saturating linear transfer function (satlins). The RMSE values for the NARX-RNN models with the different numbers of neurons in the hidden layer before and after training are presented in Table 1.
4.3 Discussion
Obtained results, presented in Table 1, indicate that touch pressure estimation improves after training around 200–300 times. The estimation errors do not depend significantly on the number of neurons in the hidden layer, even if only one neuron is used. Moreover, the number of iteration epochs is a few times lower in the case of satlins function describing neurons in the hidden layer (14–21 epochs), compared with tansig function (68–187 epochs). The obtained quality indices are similar for the ‘loading’ and ‘unloading’ phases, thus properly modelling the hysteretic behaviour of the sensor.
5 Summary
The article presents the possibility of touch pressure estimation of the e-skin graphene pressure sensors with hysteretic behaviour using NARX recurrent neural networks. Increasing the number of neurons in the nonlinear hidden layer did not improve the generalization properties of the model. Moreover, the neurons described by the simple satlins function give similar results with fewer epochs than those described with tansig.
The presented method provides a simple alternative to the e-skin graphene pressure sensors models known in the literature. Further research should be done to extend the developed model to the sensor matrix and the layered deep neural networks for e-skin calibration and data compression.
References
Alimi, A., Assaker, I.B., Mozaryn, J., Ávila Brande, D., Castillo-Martínez, E., Chtourou, R.: Electrochemical synthesis of mno2/nio/zno trijunction coated stainless steel substrate as a supercapacitor electrode and cyclic voltammetry behavior modeling using artificial neural network. Int. J. Energy Res. 46(12), 17163–17179 (2022). https://doi.org/10.1002/er.8380, https://onlinelibrary.wiley.com/doi/abs/10.1002/er.8380
Cai, M., Jiao, Z., Nie, S., Wang, C., Zou, J., Song, J.: A multifunctional electronic skin based on patterned metal films for tactile sensing with a broad linear response range. Sci. Adv. 7(52) (2021). https://doi.org/10.1126/sciadv.abl8313
Dahiya, R.: E-Skin: From Humanoids to Humans [Point of View]. Proc. IEEE 107(2), 247–252 (2019). https://doi.org/10.1109/jproc.2018.2890729
Dai, Y., Gao, S.: A flexible multi-functional smart skin for force, touch position, proximity, and humidity sensing for humanoid robots. IEEE Sens. J. 21(23), 26355–26363 (2021). https://doi.org/10.1109/jsen.2021.3055035
Dawood, A.B., Godaba, H., Ataka, A., Althoefer, K.: Silicone-based capacitive e-skin for exteroception and proprioception. In: 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 8951–8956 (2020). https://doi.org/10.1109/IROS45743.2020.9340945
Farrokh, M., Dizaji, F., Dizaji, M.: Hysteresis identification using extended preisach neural network. Neural Process. Lett. 1–25 (2022)
Hagan, M., Demuth, H., Beale, M., Orlando, D.: Neural Network Design. Martin Hagan, Stillwater, OK (2014)
Hammock, M.L., Chortos, A., Tee, B.C.K., Tok, J.B.H., Bao, Z.: 25th anniversary article: the evolution of electronic skin (E-Skin): a brief history, design considerations, and recent progress. Adv. Mater. 25(42), 5997–6038 (2013). https://doi.org/10.1002/adma.201302240
Holgado, A.C., Tomo, T.P., Somlor, S., Sugano, S.: A multimodal, adjustable sensitivity, digital 3-axis skin sensor module. Sensors 20(11), 3128 (2020). https://doi.org/10.3390/s20113128, http://dx.doi.org/10.3390/s20113128
Hu, Y., Guo, W., Long, Y., Li, S., Xu, Z.: Physics-informed deep neural networks for simulating s-shaped steel dampers. Comput. Struct. 267, 106798 (2022). https://doi.org/10.1016/j.compstruc.2022.106798, https://www.sciencedirect.com/science/article/pii/S004579492200058X
Hyndman, R.J., Koehler, A.B.: Another look at measures of forecast accuracy. Int. J. Forecast. 22(4), 679–688 (2006)
Kelley, C.: Iterative methods for optimization, SIAM front. Appl. Math. 18 (1999)
Klimaszewski, J., Janczak, D., Piorun, P.: Tactile robotic skin with pressure direction detection. Sensors 19(21) (2019). https://doi.org/10.3390/s19214697, https://www.mdpi.com/1424-8220/19/21/4697
Klimaszewski, J., Władziński, M.: Human body parts proximity measurement using distributed tactile robotic skin. Sensors 21(6) (2021). https://doi.org/10.3390/s21062138, https://www.mdpi.com/1424-8220/21/6/2138
Klimaszewski, J., Wildner, K., Ostaszewska-Liżewska, A., Władziński, M., Możaryn, J.: Robot-based calibration procedure for graphene electronic skin. Sensors 22(16) (2022). https://doi.org/10.3390/s22166122, https://www.mdpi.com/1424-8220/22/16/6122
Mayergoyz, I.D.: Mathematical Models of Hysteresis and Their Applications. Academic Press, Cambridge (2003)
Nguyen, D., Widrow, B.: Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights. In: 1990 IJCNN International Joint Conference on Neural Networks, pp. 21–26. IEEE (1990)
Oh, J.Y., Bao, Z.: Second skin enabled by advanced electronics. Adv. Sci. 6(11), 1900186 (2019). https://doi.org/10.1002/advs.201900186
Wang, F.X., et al.: Multifunctional self-powered e-skin with tactile sensing and visual warning for detecting robot safety. Adv. Mater. Interfaces 7(19), 2000536 (2020). https://doi.org/10.1002/admi.202000536
Yang, J.C., Mun, J., Kwon, S.Y., Park, S., Bao, Z., Park, S.: Electronic skin: recent progress and future prospects for skin-attachable devices for health monitoring, robotics, and prosthetics. Adv. Mater. 31(48), 1904765 (2019). https://doi.org/10.1002/adma.201904765
Zhu, L., et al.: Large-area hand-covering elastomeric electronic skin sensor with distributed multifunctional sensing capability. Adv. Intell. Syst. 4(1), 2100118 (2022). https://doi.org/10.1002/aisy.202100118, https://onlinelibrary.wiley.com/doi/abs/10.1002/aisy.202100118
Acknowledgements
This research was funded by Warsaw University of Technology, Faculty of Mechatronics Dean, grant number 504/04701/1141/44.000000.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Open Access This chapter is licensed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
The images or other third party material in this chapter are included in the chapter's Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the chapter's Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.
Copyright information
© 2023 The Author(s)
About this paper
Cite this paper
Możaryn, J. (2023). NARX Recurrent Neural Network Model of the Graphene-Based Electronic Skin Sensors with Hysteretic Behaviour. In: Biele, C., Kacprzyk, J., Kopeć, W., Owsiński, J.W., Romanowski, A., Sikorski, M. (eds) Digital Interaction and Machine Intelligence. MIDI 2022. Lecture Notes in Networks and Systems, vol 710. Springer, Cham. https://doi.org/10.1007/978-3-031-37649-8_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-37649-8_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-37648-1
Online ISBN: 978-3-031-37649-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)