Modelado de un cuello robótico blando mediante aprendizaje automático

dc.contributor.authorContinelli, Nicole A.es_ES
dc.contributor.authorNagua Cuenca, Luis Fernandoes_ES
dc.contributor.authorMonje, Concepción A.es_ES
dc.contributor.authorBalaguer, Carloses_ES
dc.contributor.funderAgencia Estatal de Investigaciónes_ES
dc.date.accessioned2023-07-10T12:29:04Z
dc.date.available2023-07-10T12:29:04Z
dc.date.issued2023-03-14
dc.description.abstract[ES] En este trabajo se aborda el problema del modelado de un cuello robótico blando mediante el uso de diferentes arquitecturas de redes neuronales, estudiando la influencia en los resultados del número de capas de cada red y de su correspondiente función de activación. Se emplearan las funciones de activación Tangente Hiperbólica (TANH) y Unidad Lineal Exponencial (ELU). Los modelos obtenidos se compararan con un modelo basado en Perceptron Multicapa (MLP) de parámetros optimizados, así comocon el modelo cinemático analítico del cuello. Los resultados experimentales obtenidos demostraran la ventaja del empleo de las técnicas de aprendizaje automático para el modelado de sistemas altamente no lineales como el del cuello robótico blando, cuya característica elástica dificulta la formulación de un modelo analítico robusto.es_ES
dc.description.abstract[EN] In this paper we address the problem of modeling a soft robotic neck by using different neural network architectures, studying the influence on the results of the number of layers of each network and its corresponding activation function. The Tangent Hyperbolic Tangent (TANH) and Exponential Linear Unit (ELU) activation functions are used. The obtained models are compared with a Multi-Layer Perceptron (MLP) with optimized parameters, as well as with the kinematic model of the neck. The experimental results demonstrate the advantage of using machine learning techniques for modeling highly nonlinear systems such as this soft robotic neck, whose elastic characteristics make it difficult to formulate a robust analytical model. en_EN
dc.description.accrualMethodOJSes_ES
dc.description.bibliographicCitationContinelli, NA.; Nagua Cuenca, LF.; Monje, CA.; Balaguer, C. (2023). Modelado de un cuello robótico blando mediante aprendizaje automático. Revista Iberoamericana de Automática e Informática industrial. 20(3):282-292. https://doi.org/10.4995/riai.2023.18752es_ES
dc.description.issue3es_ES
dc.description.referencesBecerra, Y., Arbulu, M., Soto, S., Martinez, F., 2019. A comparison among the denavit-hartenberg, the screw theory, and the iterative methods to solve inverse kinematics for assistant robot arm. In: International Conference on Swarm Intelligence. Springer, pp. 447-457. https://doi.org/10.1007/978-3-030-26369-0_42es_ES
dc.description.referencesBrownlee, J., Mastery, M. L., 2017. Deep Learning with Python: Develop Deep Learning Models on Theano and TensorFlow Using Keras. Machine Learning Mastery. URL: https://books.google.es/books?id=eJw2nQAACAAJes_ES
dc.description.referencesClevert, D.-A., Unterthiner, T., Hochreiter, S., 2015. Fast and accurate deep network learning by exponential linear units (elus).URL: https://arxiv.org/abs/1511.07289 DOI: 10.48550/ARXIV.1511.07289es_ES
dc.description.referencesContinelli, N., Nagua, L., Monje, C. A., Balaguer, C., 2022. Identificaci'on de un cuello robótico blando mediante aprendizaje automático. In: Jornadas de Robótica, Educación y Bioingeniería, pp. 124-130.es_ES
dc.description.referencesCopaci, D., Muñoz, J., González, I., Monje, C. A., Moreno, L., 2020. SMAdriven soft robotic neck: Design, control and validation. IEEE Access 8, 199492-199502. https://doi.org/10.1109/ACCESS.2020.3035510es_ES
dc.description.referencesGholamy, A., Kreinovich, V., Kosheleva, O., 2018. Why 70/30 or 80/20 relation between training and testing sets: A pedagogical explanation. International Journal of Intelligent Technologies and Applied Statistics 11 (2), 105-111.es_ES
dc.description.referencesGoodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y., 2014. Generative adversarial nets. Advances in neural information processing systems 27.es_ES
dc.description.referencesGoodfellow, I. J., Bengio, Y., Courville, A., 2016. Deep Learning. MIT Press, Cambridge, MA, USA.es_ES
dc.description.referencesHernández-Vicen, J., Martínez, S., Balaguer, C., 2021. Principios básicos para el desarrollo de una aplicaci'on de bi-manipulación de cajas por un robot humanoide. Revista Iberoamericana de Automática e Informática Industrial 18 (2), 129-137. https://doi.org/10.4995/riai.2020.13097es_ES
dc.description.referencesJin, L., Li, S., Yu, J., He, J., 2018. Robot manipulator control using neural networks: A survey. Neurocomputing 285, 23-34. https://doi.org/10.1016/j.neucom.2018.01.002es_ES
dc.description.referencesJiokou Kouabon, K., Melingui, A., Lakhal, O., Kom, M., Merzouki, R., 2020. A learning framework to inverse kinematics of redundant manipulators. IFACPapersOnLine 53 (2), 9912-9917. https://doi.org/10.1016/j.ifacol.2020.12.2699es_ES
dc.description.referencesJones, B. A., Walker, I. D., 2006. Practical kinematics for real-time implementation of continuum robots. IEEE Transactions on Robotics 22 (6), 1087- 1099. https://doi.org/10.1109/TRO.2006.886268es_ES
dc.description.referencesKöker, R., C¸ akar, T., Sari, Y., 2014. A neural-network committee machine approach to the inverse kinematics problem solution of robotic manipulators. Engineering with Computers 30 (4), 641-649. https://doi.org/10.1007/s00366-013-0313-2es_ES
dc.description.referencesMena, L., Monje, C. A., Nagua, L., Muñoz, J., Balaguer, C., 2020. Test bench for evaluation of a soft robotic link. Frontiers in Robotics and AI 7, 27. https://doi.org/10.3389/frobt.2020.00027es_ES
dc.description.referencesMuñoz, J., Monje, C. A., Nagua, L. F., Balaguer, C., 2020. A graphical tuning method for fractional order controllers based on iso-slope phase curves. ISA transactions 105, 296-307. https://doi.org/10.1016/j.isatra.2020.05.045es_ES
dc.description.referencesNagua, L., Monje, C. A., Muñoz, J., Balaguer, C., 2018a. Design and performance validation of a cable-driven soft robotic neck. In: Proc. Actas de las Jornadas Nacionales de Robótica. pp. 1-5. URL: http://hdl.handle.net/10016/30567es_ES
dc.description.referencesNagua, L., Muñoz, J., Monje, C. A., Balaguer, C., 2018b. A first approach to a proposal of a soft robotic link acting as a neck. Actas de las XXXIX Jornadas de Automática, Badajoz, 5-7 de Septiembre de 2018. https://doi.org/10.17979/spudc.9788497497565.0522es_ES
dc.description.referencesNori, F., Jamone, L., Sandini, G., Metta, G., 2007. Accurate control of a humanlike tendon-driven neck. In: 2007 7th IEEE-RAS International Conference on Humanoid Robots. IEEE, pp. 371-378. https://doi.org/10.1109/ICHR.2007.4813896es_ES
dc.description.referencesPedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P.,Weiss, R., Dubourg, V., Vanderplas, J., Passos,A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E., 2011. Scikitlearn: Machine learning in Python. Journal of Machine Learning Research 12, 2825-2830.es_ES
dc.description.referencesPerlich, C., 2010. Learning curves in machine learning. In: Encyclopedia of Machine Learning. p. 5.es_ES
dc.description.referencesReinecke, J., Deutschmann, B., Fehrenbach, D., 2016. A structurally flexible humanoid spine based on a tendon-driven elastic continuum. In: 2016 IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp. 4714-4721. https://doi.org/10.1109/ICRA.2016.7487672es_ES
dc.description.referencesRelaño, C., Muñoz, J., Monje, C. A., Martínez, S., González, D., 2022. Modeling and control of a soft robotic arm based on a fractional order control approach. Fractal and Fractional 7 (1), 8. https://doi.org/10.3390/fractalfract7010008es_ES
dc.description.referencesSegota, S. B., Andeli'c, N., Mrzljak, V., Lorencin, I., Kuric, I., Car, Z., 2021. Utilization of multilayer perceptron for determining the inverse kinematics of an industrial robotic manipulator. International Journal of Advanced Robotic Systems 18 (4), 1729881420925283. https://doi.org/10.1177/1729881420925283es_ES
dc.description.referencesSharma, S., Sharma, S., Athaiya, A., 2017. Activation functions in neural networks. towards data science 6 (12), 310-316. https://doi.org/10.33564/IJEAST.2020.v04i12.054es_ES
dc.description.referencesSiciliano, B., Khatib, O., Kr¨oger, T., 2008. Springer handbook of robotics. Vol. 200. Springer. https://doi.org/10.1007/978-3-540-30301-5es_ES
dc.description.referencesThuruthel, T. G., Falotico, E., Renda, F., Laschi, C., 2017. Learning dynamic models for open loop predictive control of soft robotic manipulators. Bioinspiration & biomimetics 12 (6), 066003. https://doi.org/10.1088/1748-3190/aa839fes_ES
dc.description.referencesTran, L., Zhang, Z., Yeo, S., Sun, Y., Yang, G., 2011. Control of a cable-driven 2-dof joint module with a flexible backbone. In: 2011 IEEE Conference on Sustainable Utilization and Development in Engineering and Technology (Student). IEEE, pp. 150-155. https://doi.org/10.1109/STUDENT.2011.6089343es_ES
dc.description.referencesWang, X., Liu, X., Chen, L., Hu, H., 2021. Deep-learning damped least squares method for inverse kinematics of redundant robots. Measurement 171, 108821. https://doi.org/10.1016/j.measurement.2020.108821es_ES
dc.description.referencesWebster III, R. J., Jones, B. A., 2010. Design and kinematic modeling of constant curvature continuum robots: A review. The International Journal of Robotics Research 29 (13), 1661-1683. https://doi.org/10.1177/0278364910368147es_ES
dc.description.referencesZaki, M. J., Meira, Jr, W., 2020. Data Mining and Machine Learning: Fundamental Concepts and Algorithms, 2nd Edition. Cambridge University Press. https://doi.org/10.1017/9781108564175es_ES
dc.description.referencesZou, J., Han, Y., So, S.-S., 2009. Overview of artificial neural networks. Artificial neural networks: methods and applications, 14-22. https://doi.org/10.1007/978-1-60327-101-1_2es_ES
dc.description.sponsorshipEsta investigación ha recibido financiación del proyecto SOFIA: Articulación blanda inteligente con capacidades de re-configuración y modularidad para plataformas robóticas, con referencia PID2020-13194GB-I00, financiado por el Ministerio de Economía, Industria y Competitividad.es_ES
dc.description.upvformatpfin292es_ES
dc.description.upvformatpinicio282es_ES
dc.description.volume20es_ES
dc.identifier.doi10.4995/riai.2023.18752
dc.identifier.eissn1697-7920
dc.identifier.issn1697-7912
dc.identifier.urihttps://riunet.upv.es/handle/10251/194758
dc.languageEspañoles_ES
dc.publisherUniversitat Politècnica de Valènciaes_ES
dc.relationino:eu-repo/grantAgreement/AEI//PID2020-113011RB-I00/ES/SOSTENIBILIDAD DEL TERCER SECTOR DE LA COMUNICACION. DISEÑO Y APLICACION DE INDICADORES/es_ES
dc.relation.ispartofRevista Iberoamericana de Automática e Informática industriales_ES
dc.relation.pasarelaOJS\18752es_ES
dc.relation.publisherversionhttps://doi.org/10.4995/riai.2023.18752es_ES
dc.relation.references10.1007/978-3-030-26369-0_42es_ES
dc.relation.references10.4995/riai.2023.18752es_ES
dc.relation.references10.1109/ACCESS.2020.3035510es_ES
dc.relation.references10.4995/riai.2020.13097es_ES
dc.relation.references10.1016/j.neucom.2018.01.002es_ES
dc.relation.references10.1016/j.ifacol.2020.12.2699es_ES
dc.relation.references10.1109/TRO.2006.886268es_ES
dc.relation.references10.1007/s00366-013-0313-2es_ES
dc.relation.references10.3389/frobt.2020.00027es_ES
dc.relation.references10.1016/j.isatra.2020.05.045es_ES
dc.relation.references10.17979/spudc.9788497497565.0522es_ES
dc.relation.references10.1109/ICHR.2007.4813896es_ES
dc.relation.references10.1007/978-0-387-30164-8_452es_ES
dc.relation.references10.1109/ICRA.2016.7487672es_ES
dc.relation.references10.3390/fractalfract7010008es_ES
dc.relation.references10.1177/1729881420925283es_ES
dc.relation.references10.33564/IJEAST.2020.v04i12.054es_ES
dc.relation.references10.1007/978-3-540-30301-5es_ES
dc.relation.references10.1088/1748-3190/aa839fes_ES
dc.relation.references10.1109/STUDENT.2011.6089343es_ES
dc.relation.references10.1016/j.measurement.2020.108821es_ES
dc.relation.references10.1177/0278364910368147es_ES
dc.relation.references10.1017/9781108564175es_ES
dc.relation.references10.1007/978-1-60327-101-1_2es_ES
dc.rightsReconocimiento - No comercial - Compartir igual (by-nc-sa)es_ES
dc.rights.accessRightsAbiertoes_ES
dc.subjectSoft roboticses_ES
dc.subjectConstant curvature (CC)es_ES
dc.subjectMachine learninges_ES
dc.subjectNeural networkes_ES
dc.subjectMultilayer perceptron (MLP)es_ES
dc.subjectActivation functiones_ES
dc.subjectRobótica blandaes_ES
dc.subjectCurvatura constante (CC)es_ES
dc.subjectAprendizaje automáticoes_ES
dc.subjectRed neuronales_ES
dc.subjectPerceptrón multicapa (MLP)es_ES
dc.subjectFuncion de activaciónes_ES
dc.titleModelado de un cuello robótico blando mediante aprendizaje automáticoes_ES
dc.title.alternativeModeling of a soft robotic neck using machine learning techniqueses_ES
dc.typeArtículoes_ES
dc.type.versioninfo:eu-repo/semantics/publishedVersiones_ES
dspace.entity.typePublication
upv.uuid98d3376e-ae1a-4fbb-abbd-b07f4b75b91ees_ES

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
ContinelliNaguaMonje - Modelado de un cuello robotico blando mediante aprendizaje automatico.pdf
Tamaño:
2.88 MB
Formato:
Adobe Portable Document Format
Descripción:
Versión editorial