Clasificación de objetos usando percepción bimodal de palpación única en acciones de agarre robótico
DOI:
https://doi.org/10.4995/riai.2019.10923Palabras clave:
Manipuladores robóticos, Percepción propioceptiva-táctil, Aprendizaje propioceptivo-táctil, Clasificación de objetos, Reconocimiento de objetosResumen
Este trabajo presenta un método para clasificar objetos agarrados con una mano robótica multidedo combinando en un descriptor híbrido datos propioceptivos y táctiles. Los datos propioceptivos se obtienen a partir de las posiciones articulares de la mano y los táctiles se extraen del contacto registrado por células de presión instaladas en las falanges. La aproximación propuesta permite identificar el objeto aprendiendo de forma implícita su geometría y rigidez usando los datos que facilitan los sensores. En este trabajo demostramos que el uso de datos bimodales con técnicas de aprendizaje supervisado mejora la tasa de reconocimiento. En la experimentación, se han llevado a cabo más de 3000 agarres de hasta 7 objetos domésticos distintos, obteniendo clasificaciones correctas del 95%con métrica F1, realizando una única palpación del objeto. Además, la generalización del método se ha verificado entrenando nuestro sistema con unos objetos y posteriormente, clasificando otros nuevos similares.
Descargas
Citas
Bae, J., Park, S., Park, J., Baeg, M., Kim, D., Oh, S., Oct 2012. Development of a low cost anthropomorphic robot hand with high capability. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 4776-4782. https://doi.org/10.1109/IROS.2012.6386063
Baishya, S. S., Bäuml, B., Oct 2016. Robust material classification with a tactile skin using deep learning. In: 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 8-15. https://doi.org/10.1109/IROS.2016.7758088
Bergquist, T., Schenck, C., Ohiri, U., Sinapov, J., Griffith, S., Stoytchev, E., 2009. Interactive object recognition using proprioceptive feedback. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)-Workshop: Semantic Perception for Robot Manipulation. URL: http://www.willowgarage.com/iros09spmm
Bishop, C., 2006. Pattern Recognition and Machine Learning. Springer-Verlag New York.
Cervantes, J., Taltempa, J., Lamont, F. G., Castilla, J. S. R., Rendon, A. Y., Jalili, L. D., 2017. Análisis comparativo de las técnicas utilizadas en un sistema de reconocimiento de hojas de planta. Revista Iberoamericana de Automática e Informática Industrial 14 (1), 104-114. https://doi.org/10.1016/j.riai.2016.09.005
Delgado, A., Corrales, J., Mezouar, Y., Lequievre, L., Jara, C., Torres, F., 2017. Tactile control based on gaussian images and its application in bi-manual manipulation of deformable objects. Robotics and Autonomous Systems 94, 148 - 161. https://doi.org/10.1016/j.robot.2017.04.017
Glorot, X., Bordes, A., Bengio, Y., 11-13 Apr 2011. Deep sparse rectifier neural networks. In: Gordon, G., Dunson, D., Dudík, M. (Eds.), Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics. Vol. 15 of Proceedings of Machine Learning Research. PMLR, Fort Lauderdale, FL, USA, pp. 315-323. URL: http://proceedings.mlr.press/v15/glorot11a.html
Guo, D., Kong, T., Sun, F., Liu, H., May 2016. Object discovery and grasp detection with a shared convolutional neural network. In: 2016 IEEE International Conference on Robotics and Automation (ICRA). pp. 2038-2043. https://doi.org/10.1109/ICRA.2016.7487351
Hastie, T., Tibshirani, R., Friedman, J., 2009. The elements of statistical learning: data mining, inference and prediction. Springer-Verlag New York. https://doi.org/10.1007/978-0-387-84858-7
Homberg, B. S., Katzschmann, R. K., Dogar, M. R., Rus, D., Sep. 2015. Haptic identification of objects using a modular soft robotic gripper. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 1698-1705. https://doi.org/10.1109/IROS.2015.7353596
Homberg, B. S., Katzschmann, R. K., Dogar, M. R., Rus, D., Mar 2019. Robust proprioceptive grasping with a soft robot hand. Autonomous Robots 43 (3), 681-696. https://doi.org/10.1007/s10514-018-9754-1
Ioffe, S., Szegedy, C., 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: 32nd International Conference on International Conference on Machine Learning. Vol. 15. JMLR, pp. 448-456.
Kang, L., Ye, P., Li, Y., Doermann, D., June 2014. Convolutional neural networks for no-reference image quality assessment. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition. pp. 1733-1740. https://doi.org/10.1109/CVPR.2014.224
Kohavi, R., 1995. A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th International Joint Conference on Artificial Intelligence - Volume 2. IJCAI'95. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, pp. 1137-1143. URL: http://dl.acm.org/citation.cfm?id=1643031.1643047
Krizhevsky, A., Sutskever, I., Hinton, G. E., 2012. Imagenet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1. NIPS'12. Curran Associates Inc., USA, pp. 1097-1105. URL: http://dl.acm.org/citation.cfm?id=2999134.2999257
Liu, H., Wu, Y., Sun, F., Guo, D., 2017a. Recent progress on tactile object recognition. International Journal of Advanced Robotic Systems 14 (4), 1729881417717056. https://doi.org/10.1177/1729881417717056
Liu, H., Yu, Y., Sun, F., Gu, J., 2017b. Visual-tactile fusion for object recognition. IEEE Transactions on Automation Science and Engineering 14 (2), 996-1008. https://doi.org/10.1109/TASE.2016.2549552
Montano, A., Su'arez, R., 2013. Object shape reconstruction based on the object manipulation. 2013 16th International Conference on Advanced Robotics, ICAR 2013, 1-6. https://doi.org/10.1109/ICAR.2013.6766571
Nasrabadi, N. M., 2007. Pattern recognition and machine learning. Journal of Electronic Imaging 16 (4). https://doi.org/10.1117/1.2819119
National Instruments, 2018. The LabView website. http://www.ni.com/en-us/shop/labview.html, online; accedido 05 Noviembre 2018.
Navarro, S. E., Gorges, N.,Wörn, H., Schill, J., Asfour, T., Dillmann, R., March 2012. Haptic object recognition for multi-fingered robot hands. In: 2012 IEEE Haptics Symposium (HAPTICS). pp. 497-502. https://doi.org/10.1109/HAPTIC.2012.6183837
Pascanu, R., Montufar, G., Bengio, Y., April 2014. On the number of inference regions of deep feed forward networks with piece-wise linear activations. In: International Conference on Learning Representations (ICLR). URL: https://arxiv.org/abs/1312.6098
Pezzementi, Z., Plaku, E., Reyda, C., Hager, G. D., June 2011. Tactile-object recognition from appearance information. IEEE Transactions on Robotics 27 (3), 473-487. https://doi.org/10.1109/TRO.2011.2125350
Powers, D. M. W., 2011. Evaluation: From precision, recall and f-measure to ROC, informedness, markedness & correlation. Journal of Machine Learning Technologies 2 (1), 37-63.
Quigley, M., Conley, K., Gerkey, B., J.Faust, Foote, T., Leibs, J., Wheeler, R., Ng, A., May 2009. Ros: an open-source robot operating system. In: IEEE International Conference on Robotics and Automation (ICRA): Workshop on Open Source Software. URL: http://www.willowgarage.com/papers/ros-open-source-robot-operating-system
Reinecke, J., Dietrich, A., Schmidt, F., Chalon, M., May 2014. Experimental comparison of slip detection strategies by tactile sensing with the biotac on the dlr hand arm system. In: IEEE International Conference on Robotics and Automation (ICRA). pp. 2742-2748. https://doi.org/10.1109/ICRA.2014.6907252
Rispal, S., Rana, A. K., Duchaine, V., 2017. Texture roughness estimation using dynamic tactile sensing. 2017 3rd International Conference on Control, Automation and Robotics, ICCAR 2017, 555-562. https://doi.org/10.1109/ICCAR.2017.7942759
Sanchez, J., Corrales, J.-A., Bouzgarrou, B.-C., Mezouar, Y., 2018. Robotic manipulation and sensing of deformable objects in domestic and industrial applications: a survey. The International Journal of Robotics Research 37 (7), 688-716. https://doi.org/10.1177/0278364918779698
Schmitz, A., Bansho, Y., Noda, K., Iwata, H., Ogata, T., Sugano, S., Nov 2014. Tactile object recognition using deep learning and dropout. In: 2014 IEEERAS International Conference on Humanoid Robots. pp. 1044-1050. https://doi.org/10.1109/HUMANOIDS.2014.7041493
Schneider, A., Sturm, J., Stachniss, C., Reisert, M., Burkhardt, H., Burgard,W., Oct 2009. Object identification with tactile sensors using bag-of-features. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 243-248. https://doi.org/10.1109/IROS.2009.5354648
Shalabi, L., Shaaban, Z., Kasasbeh, B., David, M., 2006. Data mining: A preprocessing engine. Journal of Computer Science 2 (9), 735-739. https://doi.org/10.3844/jcssp.2006.735.739
Sinapov, J., Bergquist, T., Schenck, C., Ohiri, U., Griffith, S., Stoytchev, A., 2011. Interactive object recognition using proprioceptive and auditory feedback. The International Journal of Robotics Research 30 (10), 1250-1262. https://doi.org/10.1177/0278364911408368
Spiers, A. J., Liarokapis, M. V., Calli, B., Dollar, A. M., apr 2016. Single-Grasp Object Classification and Feature Extraction with Simple Robot Hands and Tactile Sensors. IEEE Transactions on Haptics 9 (2), 207-220. URL: http://ieeexplore.ieee.org/document/7390277/ https://doi.org/10.1109/TOH.2016.2521378
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R., 2014. Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research 15, 1929-1958. URL: http://jmlr.org/papers/v15/srivastava14a.html
Tekscan, 2018. The Tekscan website. https://www.tekscan.com, online; accedido 05 Noviembre 2018.
Velasco-Sanchez, 2018. Base de datos de agarres con Allegro y Tekscan. https://github.com/EPVelasco/Descriptores de agares, online; accedido 05 Noviembre 2018.
Velasco-Sanchez, E., Zapata-Impata, B. S., Gil, P., Torres, F., 2018. Reconocimiento de objetos agarrados con sensorizado híbrido propioceptivo-táctil. In: XXXIX Jornadas de Automática. CEA-IFAC, pp. 224-232. URL: https://www.eweb.unex.es/eweb/ja2018/actas.html
Vásquez, A., Perdereau, V., 2017. Proprioceptive shape signatures for object manipulation and recognition purposes in a robotic hand. Robotics and Autonomous Systems 98, 135 - 146. URL: http://www.sciencedirect.com/science/article/pii/S092188901630700X https://doi.org/10.1016/j.robot.2017.06.001
Zapata-Impata, B. S., Gil, P., Torres, F., 2018. Non-matrix tactile sensors: How can be exploited their local connectivity for predicting grasp stability? In: IEEE/RSJ International Conference on Intelligent Robots And Systems (IROS). Workshop on Robotac: New Progress in Tactile Perception And Learning in Robotics. IEEE. URL: https://arxiv.org/abs/1809.05551
Zapata-impata, B. S., Gil, P., Torres, F., 2019. Learning Spatio Temporal Tactile Features with a ConvLSTM for the Direction Of Slip Detection. Sensors 19 (3), 1-16. URL: https://www.mdpi.com/1424-8220/19/3/523 DOI: 10.3390/s19030523 https://doi.org/10.3390/s19030523
Descargas
Publicado
Cómo citar
Número
Sección
Licencia
Esta revista se publica bajo una Licencia Creative Commons Attribution-NonCommercial-CompartirIgual 4.0 International (CC BY-NC-SA 4.0)
