Generalización de las trayectorias de un brazo robótico utilizando primitivas de movimiento dinámico y regresión de procesos gaussianos.
Generalización de las trayectorias de un brazo robótico utilizando primitivas de movimiento dinámico y regresión de procesos gaussianos.
Contenido principal del artículo
Resumen
Es común encontrar robots realizando tareas en áreas compartidas con humanos, donde se espera que sean capaces de aprender de las acciones realizadas por otros y de adaptarse a nuevas situaciones. En este trabajo, se capturan las trayectorias del brazo de un operario mientras se mueve para agarrar un objeto, realizando seguimiento de articulaciones con el sensor kinect de Microsoft. La técnica utilizada para la codificación de las señales de entrenamiento se denominan primitivas de movimiento dinámico (DMP), mientras que la reconstrucción se realiza mediante regresión de procesos gaussianos (GPR). GPR permite además, generalizar los movimientos de entrenamiento a nuevas trayectorias, cuando cambian tanto la posición inicial de la mano como la ubicación del objeto. La técnica de generalización se compara contra un algoritmo basado en distancia de Mahalanobis y distribución gaussiana, que utiliza los datos de la trayectoria sin codificar, para realizar la estimación. La técnica propuesta presentó bajos tiempos de codificación y errores pequeños con respecto a los valores objetivo al probarlo con 30 puntos de consulta para el valor inicial de la mano, y 30 puntos para la posición final.
Descargas
Detalles del artículo
Referencias (VER)
De Maesschalck, R., Jouan-Rimbaud, D., and Massart, D. L. (2000). The mahalanobis distance. Chemometrics and intelligent laboratory systems, 50 (1), pp. 1–18.
Forte, D., Gams, A., Morimoto, J., and Ude, A. (2012). On-line motion synthesis and adaptation using a trajectory database. Robotics and Autonomous Systems, 60 (10), pp. 1327–1339.
Forte, D., Ude, A., and Gams, A. (2011). Real-time generalization and integration of different movement primitives. In 2011 11th IEEE-RAS International Conference on Humanoid Robots (Humanoids), pp. 590–595.
Gams, A. and Ude, A. (2009). Generalization of example movements with dynamic systems. In 2009 9th IEEE-RAS International Conference on Humanoid Robots (Humanoids), pp. 28–33.
Kaneko, T., Ono, T., and Munakata, N. (2011). Implementation of context-adaptive physical imitation between humans and robots. In 2011 IEEE RO-MAN, pp. 187 –191.
Kober, J., Oztop, E., and Peters, J. (2011). Reinforcement learning to adjust robot movements to new situations. In IJCAI Proceedings-International Joint Conference on Artificial Intelligence, volume 22, pp. 2650.
Kormushev, P., Calinon, S., and Caldwell, D. G. (2011). Imitation learning of positional and force skills demonstrated via kinesthetic teaching and haptic input. Advanced Robotics, 25 (5): 581–603.
Kormushev, P., Calinon, S., Saegusa, R., and Metta, G. (2010). Learning the skill of archery by a humanoid robot icub. In 2010 10th IEEE-RAS International Conference on Humanoid Robots (Humanoids), pages 417–423.
Kulvicius, T., Ning, K., Tamosiunaite, M., and Worgotter, F. (2012). Joining movement sequences: Modified dynamic movement primitives for robotics applications exemplified on handwriting. IEEE Transactions on Robotics, 28 (1): 145–157.
Lee, A. X., Huang, S. H., Hadfield-Menell, D., Tzeng, E., and Abbeel, P. (2014). Unifying scene registration and trajectory optimization for learning from demonstrations with application to manipulation of deformable objects. In 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2014), pages 4402–4407.
León, A., Morales, E., Altamirani, L., and Ruiz, J. (2011). Teaching a robot new tasks through imitation and on-line feedback. In Proc. of the 16th Iberoamerican Congress on Pattern Recognition.
Lopes, M., Melo, F., Montesano, L., and Santos-Victor, J. (2010). Abstraction levels for robotic imitation: Overview and computational approaches. In Sigaud, O. and Peters, J., editors, From Motor Learning to Interaction Learning in Robots, volume 264 of Studies in Computational Intelligence, pages 313–355. Springer Berlin / Heidelberg.
Lopes, M. and Santos-Victor, J. (2007). A developmental roadmap for learning by imitation in robots. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 37 (2): 308–321.
Metta, G., Sandini, G., Vernon, D., Natale, L., and Nori, F. (2008). The icub humanoid robot: an open platform for research in embodied cognition. In Proceedings of the 8th Workshop on Performance Metrics for Intelligent Systems, PerMIS ’08, pp. 50–56, New York, NY, USA. ACM.
Natale, L., Nori, F., Metta, G., Fumagalli, M., Ivaldi, S., Pattacini, U., Randazzo, M., Schmitz, A., and Sandini, G. (2013). The icub platform: a tool for studying intrinsically motivated learning. In Intrinsically motivated learning in natural and artificial systems, pp. 433–458. Springer.
Nath, V. K. and Levinson, S. E. (2012). Learning to fire at targets by an icub humanoid robot. Urbana, 51, pp. 61801.
Nemec, B. and Ude, A. (2012). Action sequencing using dynamic movement primitives. Robotica, 30(5), pp.837.
Nguyen-Tuong, D., Seeger, M., and Peters, J. (2009). Model learning with local gaussian process regression. Advanced Robotics, 23(15), pp.2015–2034.
Nicolescu, M. N. and Mataric, M. J. (2005). Task learning through imitation and human-robot interaction. In Models and Mechanisms of Imitation and Social Learning in Robots, Humans and Animals: Behavioural, Social and Communicative Dimensions, pp. 407–424. University Press.
Oikonomidis, I., Kyriazis, N., and Argyros, A. (2011). Efficient model-based 3d tracking of hand articulations using kinect. In BMVC 2011. BMVA.
Pastor, P., Hoffmann, H., Asfour, T., and Schaal, S. (2009). Learning and generalization of motor skills by learning from demonstration. In 2009 IEEE International Conference on Robotics and Automation (ICRA), pp. 763-768.
Peña-Solórzano, C.; Hoyos-Gutiérrez, J.; Prieto- Ortiz, F. (2015). Hacia el agarre de objetos utilizando aprendizaje robótico por imitación y datos de fuerza. Revista EIA, 12 (23) Enero-Junio, pp. 71-82.
Rasmussen, C. E. (2004). Gaussian processes in machine learning. In Advanced Lectures on Machine Learning, pp. 63–71. Springer.
Stulp, F., Theodorou, E., Buchli, J., and Schaal, S. (2011). Learning to grasp under uncertainty. In 2011 IEEE International Conference on Robotics and Automation (ICRA), pp. 5703–5708.
Tamosiunaite, M., Nemec, B., Ude, A., and Wörgötter, F. (2011). Learning to pour with a robot arm combining goal and shape learning for dynamic movement primitives. Robotics and Autonomous Systems, 59 (11), pp. 910–922.
Tan, H., Erdemir, E., Kawamura, K., and Du, Q. (2011). A potential field method-based extension of the dynamic movement primitive algorithm for imitation learning with obstacle avoidance. In 2011 International Conference on Mechatronics and Automation (ICMA), pp. 525–530.
Tikhanoff, V., Cangelosi, A., and Metta, G. (2011). Integration of speech and action in humanoid robots: icub simulation experiments. IEEE Transactions on Autonomous Mental Development, 3 (1), pp. 17–29.
Toda, Y., Kodai, Y., Hiwada, E., and Kubota, N. (2011). Human motion tracking for cognitive rehabilitation in informationally structured space based on sensor networks. In 2011 IEEE International Conference on Fuzzy Systems (FUZZ), pp. 1459 –1465.
Ude, A., Gams, A., Asfour, T., and Morimoto, J. (2010). Task-specific generalization of discrete and periodic dynamic movement primitives. IEEE Transactions on Robotics, 26 (5), pp. 800–815.