آموزش تقلیدی حرکات پیچیده به ربات‌های انسان‌نما به کمک بهینه سازی تکاملی شبکه‌ عصبی مولد الگوی واحد

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشکده مهندسی مکانیک، دانشگاه اصفهان، اصفهان، ایران

2 دانشکده مهندسی کامپیوتر، دانشگاه اصفهان، اصفهان، ایران

چکیده

در این مقاله یک سامانه مبتنی بر ساختارهای عصبی موسوم به مولد مرکزی الگوی واحد ارائه شده که قادر است الگوی موردنیاز برای حرکت در یک ربات را براساس یک نوع آموزش نمایشی به دست آورد. مولد الگوی واحد می‌تواند به دو زیرسامانه گسسته و ریتمیک تقسیم‌بندی شود. زیرسامانه اول مسئولیت تولید حرکات کوتاه و معطوف به هدف و زیرسامانه دوم مسئولیت تولید حرکات ریتمیک را به عهده دارد. الگوریتم آموزشی خاصی برای استفاده از این مولدهای الگوی واحد در این مقاله طراحی شده است. مفاصل و بازوهای ربات با تشخیص اسکلت بدن انسان توسط حسگر کینکت به‌صورت بلادرنگ کنترل می‌شوند. اساس کار انجام شده بدین شکل است که ابتدا به کمک حسگر کینکت دنباله های حرکتی بدن مربی ضبط شده و به کامپیوتر منتقل می‌شوند. این دنباله‌های حرکتی تعدادی نوسان سازهای غیرخطی را آموزش داده و سپس نوسان سازهای غیرخطی حرکات را برای ربات انسان نما بازتولید می‌کنند. برای ارزیابی نتایج سیگنال‌های آموزش داده شده در نرم افزار وی رپ شبیه سازی شده و سپس بر روی ربات انسان نمای بایولوید پیاده سازی شدند. مدل ارائه شده یک بستر مناسب جهت ارائه آموزش‌های نمایشی و مبتنی بر تقلید برای ربات‌های انسان‌نما محسوب می‌شود که نیاز به کنترل صریح و برنامه نویسی مستقیم را برطرف می‌سازد و امکان آموزش غیرمستقیم رفتارهای پیچیده روی انواع ربات ها را مهیا می‌سازد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Imitation Learning of Complex Behaviors to Humanoid Robots using Evolutionary Optimization of Neural Network of Unit Pattern Generator

نویسندگان [English]

  • B. Khodabandeh 1
  • H. Shahbazi 1
  • A. Monadjemi 2
1 Department of Mechanical Engineering, University of Isfahan, Isfahan, Iran
2 Department of Computer Engineering, University of Isfahan, Isfahan, Iran
چکیده [English]

In this paper, a system based on neural structures known as central pattern generator is presented which enables to acquire the required patterns to move a robot based on a demonstration training. Unit pattern generator can be divided to two subsystems, one is a rhythmic system and the other is a discrete system. The first subsystem is responsible to produce short movements and the second subsystem is responsible to produce rhythmic movements. The special learning algorithm is designed to use these unit pattern generators. Joints and limbs of robot were controlled by Kinect sensor in real time by recognition of the human body skeleton. The work steps were done in this way that the motion sequences of teacher’ body were recorded by Kinect sensor, then transmitted to the computer. These motion sequences teach some nonlinear oscillators then they reproduce motions for humanoid robot. As a result, humanoid body joints imitate the teacher movement in a real time. The main contribution of this paper is design of this learning algorithm which is able to simultaneously search for the weights and topology of the network the algorithm synchronize the neural network by coupling the neurons at the last stage.

کلیدواژه‌ها [English]

  • Humanoid robot
  • Imitation learning
  • Nonlinear oscillator
  • Central pattern generator
  • Kinect microsoft
[1] H. Shahbazi, K. Jamshidi, A.H. Monadjemi, H. Eslami, Biologically inspired layered learning in humanoid robots, Knowledge-Based Systems, 57 (2014) 8-27.
[2] L. Rozo, Robot learning from demonstration of force-based manipulation tasks, (2013).
[3] S. Schaal, Is imitation learning the route to humanoid robots?, Trends in cognitive sciences, 3(6) (1999) 233-242.
[4] O.C. Jenkins, M.J. Mataric, S. Weber, Primitive-based movement classification for humanoid imitation, in: Proceedings of the 1st IEEE-RAS International Conference on Humanoid Robotics, 2000.
[5] H. Asada, H. Izumi, Automatic program generation from teaching data for the hybrid control of robots, IEEE Transactions on Robotics and Automation, 5(2) (1989) 166-173.
[6] C.G. Atkeson, S. Schaal, Learning tasks from a single demonstration, in: Robotics and Automation, 1997. Proceedings., 1997 IEEE International Conference on, IEEE, 1997, pp. 1706-1712.
[7] D. Perrett, P. Smith, A. Mistlin, A. Chitty, A. Head, D. Potter, R. Broennimann, A. Milner, M. Jeeves, Visual analysis of body movements by neurones in the temporal cortex of the macaque monkey: a preliminary report, Behavioural brain research, 16(2) (1985) 153-170.
[8] N. Das, R. Prakash, L. Behera, Learning object manipulation from demonstration through vision for the 7-DOF barrett WAM, in: 2016 IEEE First International Conference on Control, Measurement and Instrumentation (CMI), IEEE, 2016, pp. 391-396.
[9] A. Zaraki, M. Giuliani, M.B. Dehkordi, D. Mazzei, A. D'ursi, D. De Rossi, An rgb-d based social behavior interpretation system for a humanoid social robot, in: Robotics and Mechatronics (ICRoM), 2014 Second RSI/ISM International Conference on, IEEE, 2014, pp. 185-190.
[10] B.D. Argall, S. Chernova, M. Veloso, B. Browning, A survey of robot learning from demonstration, Robotics and autonomous systems, 57(5) (2009) 469-483.
[11] T.I.M.I.H. INOUE, M. Inamura, H. Inaba, Acquisition of probabilistic behavior decision model based on the interactive teaching method, in: Proceedings of the Ninth International Conference on Advanced Robotics, ICAR99, 1999.
[12] W.D. Smart, Making reinforcement learning work on real robots, Brown University, 2002.
[13] J.A. Clouse, On integrating apprentice learning and reinforcement learning, (1996).
[14] R.P. Rao, A.P. Shon, A.N. Meltzoff, A Bayesian model of imitation in infants and robots, Imitation and social learning in robots, humans, and animals, (2004) 217-247.
[15] T. Asfour, P. Azad, F. Gyarfas, R. Dillmann, Imitation learning of dual-arm manipulation tasks in humanoid robots, International Journal of Humanoid Robotics, 5(02) (2008) 183-202.
[16] D. Herzog, A. Ude, V. KrUger, Motion imitation and recognition using parametric hidden markov models, in: Humanoids 2008-8th IEEE-RAS International Conference on Humanoid Robots, IEEE, 2008, pp. 339-346.
[17] V. KR, D.L.H. UGER, S. Baby, Primitive-Based Modeling and Grammar, IEEE robotics & automation magazine, (2010) 31.
[18] A.J. Ijspeert, J. Nakanishi, S. Schaal, Movement imitation with nonlinear dynamical systems in humanoid robots, in: Robotics and Automation, 2002. Proceedings. ICRA'02. IEEE International Conference on, IEEE, 2002, pp. 1398-1403.
[19] S. Schaal, J. Peters, J. Nakanishi, A. Ijspeert, Learning movement primitives, in: Robotics Research. The Eleventh International Symposium, Springer, 2005, pp. 561-572.
[20] H. Shahbazi, K. Jamshidi, A.H. Monadjemi, Sensor-based programming of central pattern generators in humanoid robots, International Journal of Advanced Robotic Systems, 10 (2013).
[21] L. Righetti, A.J. Ijspeert, Programmable central pattern generators: an application to biped locomotion control, in: Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006., IEEE, 2006, pp. 1585-1590.
[22] S. Degallier, L. Righetti, S. Gay, A. Ijspeert, Toward simple control for complex, autonomous robotic applications: combining discrete and rhythmic motor primitives, Autonomous Robots, 31(2-3) (2011) 155-181.
[23] S. Gay, J. Santos-Victor, A. Ijspeert, Learning robot gait stability using neural networks as sensory feedback function for central pattern generators, in: Intelligent Robots and Systems (IROS), 2013 IEEE/RSJ International Conference on, Ieee, 2013, pp. 194-201.
[24] J. Nicolas, Artificial evolution of controllers based on non-linear oscillators for bipedal locomotion, Master's thesis, EPFL, winter, 2006 (2005).
[25] T. Wei, Y. Qiao, B. Lee, Kinect skeleton coordinate calibration for remote physical training, in: Proceedings of the International Conference on Advances in Multimedia (MMEDIA), 2014, pp. 23-27.
[26] Y. Ou, J. Hu, Z. Wang, Y. Fu, X. Wu, X. Li, A real-time human imitation system using kinect, International Journal of Social Robotics, 7(5) (2015) 587-600.
[27] H. Ma, H. Wang, M. Fu, C. Yang, One new human-robot cooperation method based on kinect sensor and visual-servoing, in: International Conference on Intelligent Robotics and Applications, Springer, 2015, pp. 523-534.
[28] R. PARANDEH, H. SHAHBAZI, K. JAMSHIDI, J.B. KHODABANDEH, Design of a Trainable Controller Inspired from Neural System to Generate Complex Behaviors in Humanoid Robots, (2016).
[29] M.A. Arshi, Imitation learning of playing songs in humanoid robot simulator, University of Isfahan, Isfahan, 2014.