EMG-Based Grasping Force Estimation for Robot Skill Transfer Learning

W. Ali ; S. Kolyubin

Russian journal of nonlinear dynamics, Tome 18 (2022) no. 5, pp. 859-872.

Résumé

In this study, we discuss a new machine learning architecture, the multilayer preceptron- random forest regressors pipeline (MLP-RF model), which stacks two ML regressors of different kinds to estimate the generated gripping forces from recorded surface electromyographic activity signals (EMG) during a gripping task. We evaluate our proposed approach on a publicly available dataset, putEMG-Force, which represents a sEMG-Force data profile. The sEMG signals were then filtered and preprocessed to get the features-target data frame that will be used to train the proposed ML model. The proposed ML model is a pipeline of stacking 2 different natural ML models; a random forest regressor model (RF regressor) and a multiple layer perceptron artificial neural network (MLP regressor). The models were stacked together, and the outputs were penalized by a Ridge regressor to get the best estimation of both models. The model was evaluated by different metrics; mean squared error and coefficient of determination, or r2 score, to improve the model prediction performance. We tuned the most significant hyperparameters of each of the MLP-RF model components using a random search algorithm followed by a grid search algorithm. Finally, we evaluated our MLP-RF model performance on the data by training a recurrent neural network consisting of 2 LSTM layers, 2 dropouts, and one dense layer on the same data (as it is the common approach for problems with sequential datasets) and comparing the prediction results with our proposed model. The results show that the MLP-RF outperforms the RNN model.

Détail

Keywords: sEMG signals, random forest regressor (RF), recurrent neural network (RNN), robot grasping forces, skill transfer learning.
Mots-clés : multilayer perceptron regressor (MLP)

Bibliographie

[1] Torabi, F., Warnell, G., and Stone, P., “Behavioral Cloning from Observation”, Proc. of the 27th Internat. Joint Conf. on Artificial Intelligence (IJCAI'18, Stockholm, Sweden, Jul 2018), 8 pp.

[2] Ho, J. and Ermon, S., “Generative Adversarial Imitation Learning”, 30th Conf. on Neural Information Processing Systems (NIPS, Barcelona, Spain, Dec 2016), 9 pp.

[3] Hadfield-Menell, D., Dragan, A., Abbeel, P., and Russell, S., “Cooperative Inverse Reinforcement Learning”, 30th Conf. on Neural Information Processing Systems (NIPS, Barcelona, Spain, Dec 2016), 9 pp.

[4] Uchida, N., Hiraiwa, A., Sonehara, N., and Shimohara, K., “EMG Pattern Recognition by Neural Networks for Multi Fingers Control”, Proc. of the 14th Annual Internat. Conf. of the IEEE Engineering in Medicine and Biology Society (Paris, France, Oct 1992), v. 3, 1016–1018

[5] Kelly, M. F., Parker, P. A., and Scott, R. N., “The Application of Neural Networks to Myoelectric Signal Analysis: A Preliminary Study”, IEEE Trans. Biomed. Eng., 37:3 (1990), 221–230

[6] Koike, Y. and Kawato, M., “Estimation of Arm Posture in 3D-Space from Surface EMG Signals Using a Neural Network Model”, IEICE Transactions Fundamentals, E77-D:4 (1994), 368–375

[7] Huang, H.-P. and Chen, Ch.-Y.“, Development of a Myoelectric Discrimination System for a Multi-Degree Prosthetic Hand”, Proc. of the IEEE Internat. Conf. on Robotics and Automation (Detroit, Mich., May 1999), v. 3, 2392–2397

[8] Kaczmarek, P., Mańkowski, T., and Tomczyński, J., “putEMG — A Surface Electromyography Hand Gesture Recognition Dataset”, Sensors, 19:16 (2019), 3548, 17 pp.

[9] Kursa, M. and Rudnicki, W., The All Relevant Feature Selection Using Random Forest, 16 pp., arXiv: 1106.5112 [cs.AI]

[10] Romero, E. and Sopena, J., “Performing Feature Selection with Multilayer Perceptrons”, IEEE Trans. Neural Netw., 19:3 (2008), 431–441

[11] John, G. H., Kohavi, R., and Pfleger, K., “Irrelevant Features and the Subset Selection Problem”, Proc. of the 11th Internat. Conf. on Machine Learning (Rutgers University, New Brunswick, N.J., Jul 1994), 121–129

[12] Breiman, L., “Stacked Regressions”, Machine Learning, 24:1 (1996), 49–64

[13] Lim, Y., Stacked Ensembles Improving Model Performance on a Higher Level, Towards Data Science, 25 Mar 2021

[14] Hilt, D. E. and Seegrist, D. W., Ridge: A Computer Program for Calculating Ridge Regression Estimates, Research Note NE-236, U.S. Department of Agriculture, Forest Service, Northeastern Forest Experiment Station, Upper Darby, Pa., 1977, 7 pp.

[15] Al-Muhammed, M. J. and Zitar, R. A., “Probability-Directed Random Search Algorithm for Unconstrained Optimization Problem”, Appl. Soft Comput., 71 (2018), 165–182

[16] Menke, W., Geophysical Data Analysis: Discrete Inverse Theory, 3rd ed, Elsevier, Amsterdam, 2012, 330 pp.

[17] Ho, T. K., Random Decision Forests, Proc. of the 3rd Internat. Conf. on Document Analysis and Recognition (Montreal, QC, Aug 1995), v. 1, 278–282

[18] Zabinsky, Z. B., “Random Search Algorithms”, Wiley Encyclopedia of Operations Research and Management Science, eds. J. J. Cochran, L. A. Cox, P. Keskinocak, J. P. Kharoufeh, J. C. Smith, Wiley, Hoboken, N.J., 2010

[19] Liashchynskyi, P. and Liashchynskyi, P., Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS, 11 pp., arXiv: 1912.06059 [cs.LG]

[20] Hastie, T., Tibshirani, R., and Friedman, J., The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed, Springer, New York, 2009, XXII, 745 pp.

[21] Stone, M., “An Asymptotic Equivalence of Choice of Model by Cross-Validation and Akaike's Criterion”, J. R. Stat. Soc. Series B Stat. Methodol., 39:1 (1977), 44–47

[22] Recurrent Neural Networks: Design and Applications, eds. L. R. Medsker, L. C. Jain, CRC, Boca Raton, Fla., 1999, 416 pp.

[23] Graves, A., “Long Short-Term Memory”, Supervised Sequence Labelling with Recurrent Neural Networks, Stud. Comput. Intell., 385, Springer, Berlin, 2012, 37–45