Hostname: page-component-586b7cd67f-g8jcs Total loading time: 0 Render date: 2024-11-22T15:43:04.107Z Has data issue: false hasContentIssue false
  • English
  • Français

Compliant Parametric Dynamic Movement Primitives

Published online by Cambridge University Press:  31 May 2019

Emre Ugur Open the ORCID record for Emre Ugur [Opens in a new window]  and
Hakan Girgin
Emre Ugur*
Affiliation:
Bogazici University, Computer Engineering, Istanbul, Turkey. E-mail: [email protected]
Hakan Girgin
Affiliation:
Bogazici University, Computer Engineering, Istanbul, Turkey. E-mail: [email protected]
*
*Corresponding author. E-mail: [email protected]
Get access Rights & Permissions [Opens in a new window]

Summary

In this paper, we propose and implement an advanced manipulation framework that enables parametric learning of complex action trajectories along with their haptic feedback profiles. Our framework extends Dynamic Movement Primitives (DMPs) method with a new parametric nonlinear shaping function and a novel force-feedback coupling term. The nonlinear trajectories of the action control variables and the haptic feedback trajectories measured during execution are encoded with parametric temporal probabilistic models, namely parametric hidden Markov models (PHMMs). PHMMs enable autonomous segmentation of a taught skill based on the statistical information extracted from multiple demonstrations, and learning the relations between the model parameters and the properties extracted from the environment. Hidden states with high-variances in observation probabilities are interpreted as parts of the skill that could not be reliably learned and autonomously executed due to possibly uncertain or missing information about the environment. In those parts, our proposed force-feedback coupling term, which computes the deviation of the actual force feedback from the one predicted by the force-feedback PHMM, acts as a compliance term, enabling a human to scaffold the ongoing movement trajectory to accomplish the task. Our method is verified in a number of tasks including a real pick and place task that involves obstacles of different heights. Our robot, Baxter, successfully learned to generate the trajectory taking into the heights of the obstacles, move its end effector stiffly (and accurately) along the generated trajectory while passing through apertures, and allow human–robot collaboration in the autonomously detected segments of the motion, for example, when the gripper picks up the object whose position is not provided to the robot.

Keywords

Learning from demonstrationDynamic movement primitivesHidden Markov modelsParametric actionsHaptic feedback models
Type
Articles
Information
Robotica , Volume 38 , Issue 3 , March 2020 , pp. 457 - 474
Copyright
© Cambridge University Press 2019 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Pratt, G. A., “Is a cambrian explosion coming for robotics?” J. Econ. Persp. 29(3), 51–60 (2015).CrossRefGoogle Scholar
Gibson, J. J., The Ecological Approach to Visual Perception (Lawrence Erlbaum Associates, Hillsdale, New Jersey, 1986).Google Scholar
Ugur, E., Oztop, E. and Sahin, E., “Goal emulation and planning in perceptual space using learned affordances,” Rob. Auto. Syst. 59(7–8), 580–595 (2011).CrossRefGoogle Scholar
Pastor, P., Righetti, L., Kalakrishnan, M. and Schaal, S., “Online Movement Adaptation Based on Previous Sensor Experiences,” 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), San Francisco, CA (IEEE, 2011) pp. 365–371.Google Scholar
Argall, B. D., Chernova, S., Veloso, M. and Browning, B., “A survey of robot learning from demonstration,” Rob. Auto. Syst. 57(5), 469–483 (2009).CrossRefGoogle Scholar
Schaal, S., “Dynamic Movement Primitives-a Framework for Motor Control in Humans and Humanoid Robotics,” In: Adaptive Motion of Animals and Machines (Kimura, H., Tsuchiya, K., Ishiguro, A., Witte, H. eds) (Springer, Tokyo, 2006) pp. 261–280.CrossRefGoogle Scholar
Pastor, P., Kalakrishnan, M., Chitta, S., Theodorou, E. and Schaal, S., “Skill Learning and Task Outcome Prediction for Manipulation,” 2011 IEEE International Conference on Robotics and Automation (ICRA), Shanghai (IEEE, 2011) pp. 3828–3834.CrossRefGoogle Scholar
Colomé, A. and Torras, C., “Dimensionality Reduction and Motion Coordination in Learning Trajectories with Dynamic Movement Primitives,” 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Chicago (IEEE, 2014) pp. 1414–1420.CrossRefGoogle Scholar
Calinon, S., Evrard, P., Gribovskaya, E., Billard, A. and Kheddar, A., “Learning Collaborative Manipulation Tasks by Demonstration Using a Haptic Interface,” 2009 International Conference on Advanced Robotics (ICAR), Munich (IEEE, 2009) pp. 1–6.Google Scholar
Asfour, T., Azad, P., Gyarfas, F. and Dillmann, R., “Imitation learning of dual-arm manipulation tasks in humanoid robots,” Int. J. Hum. Rob. 5(02), 183–202 (2008).CrossRefGoogle Scholar
Amor, H. B., Kroemer, O., Hillenbrand, U., Neumann, G. and Peters, J., “Generalization of Human Grasping for Multi-fingered Robot Hands,” 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Algarve, Portugal (IEEE, 2012) pp. 2043–2050.CrossRefGoogle Scholar
Mühlig, M., Gienger, M. and Steil, J. J., “Interactive imitation learning of object movement skills,” Auto.Rob. 32(2), 97–114 (2012).CrossRefGoogle Scholar
Lee, D. and Ott, C., “Incremental kinesthetic teaching of motion primitives using the motion refinement tube,” Auto. Rob. 31(2–3), 115–131 (2011).CrossRefGoogle Scholar
Atkeson, C. G., Moore, A. W. and Schaal, S., “Locally Weighted Learning for Control,” In: Lazy Learning (Aha, David W. ed.) (Springer, Dordrecht, 1997) pp. 75–113.CrossRefGoogle Scholar
Vijayakumar, S. and Schaal, S., “Locally Weighted Projection Regression: Incremental Real Time Learning in High Dimensional Space,” Proceedings of the Seventeenth International Conference on Machine Learning (Morgan Kaufmann Publishers Inc., Massachusetts, United States, 2000) pp. 1079–1086.Google Scholar
Calinon, S., Guenter, F. and Billard, A., “On learning, representing, and generalizing a task in a humanoid robot,” Part B Cyber. IEEE Trans. Syst. Man Cyber. 37(2), 286–298 (2007).CrossRefGoogle Scholar
Zhou, Y. and Asfour, T., “Task-Oriented Generalization of Dynamic Movement Primitive,” 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver (2017) pp. 3202–3209.CrossRefGoogle Scholar
Ude, A., Gams, A., Asfour, T. and Morimoto, J., “Task-specific generalization of discrete and periodic dynamic movement primitives,” IEEE Trans. Rob. 26(5), 800–815 (2010).CrossRefGoogle Scholar
Pervez, A. and Lee, D., “Learning task parameterized dynamic movement primitives using mixture of gmms,” Int. Service Robot. (2017). http://elib.dlr.de/113356/Google Scholar
Pastor, P., Kalakrishnan, M., Righetti, L. and Schaal, S., “Towards Associative Skill Memories,” 2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids), Osaka, Japan (IEEE, 2012) pp. 309–315.CrossRefGoogle Scholar
Pastor, P., Hoffmann, H., Asfour, T. and Schaal, S., “Learning and Generalization ofMotor Skills by Learning from Demonstration,” IEEE International Conference on Robotics and Automation, 2009 (ICRA’09), Kobe, Japan (IEEE, 2009) pp. 763–768.CrossRefGoogle Scholar
Chu, V., McMahon, I., Riano, L., McDonald, C. G., He, Q., Martinez Perez-Tejada, J.,Arrigo, M., Fitter, N., Nappo, J. C., Darrell, T. and Kuchenbecker, K. J., “Using Robotic Exploratory Procedures to Learn the Meaning of Haptic Adjectives,” 2013 IEEE International Conference on Robotics and Automation (ICRA), Kobe, Japan (IEEE, 2013) pp. 3048–3055.CrossRefGoogle Scholar
Araki, T., Nakamura, T., Nagai, T., Funakoshi, K., Nakano, M. and Iwahashi, N., “Autonomous Acquisition of Multimodal Information for Online Object Concept Formation by Robots,” 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), San Francisco, CA (IEEE, 2011) pp. 1540–1547.CrossRefGoogle Scholar
Droniou, A., Ivaldi, S. and Sigaud, O., “Deep unsupervised network for multimodal perception, representation and classification,” Rob. Auto. Syst. 71, 83–98 (2015).CrossRefGoogle Scholar
Kramberger, A., Gams, A., Nemec, B., Chrysostomou, D., Madsen, O. and Ude, A., “Generalization of orientation trajectories and force-torque profiles for robotic assembly,” Robot. Auton. Syst. 98, 333–346 (2017). https://doi.org/10.1016/j.robot.2017.09.019CrossRefGoogle Scholar
Wilson, A. D. and Bobick, A. F., “Parametric hidden Markov models for gesture recognition,” IEEE Trans.Pattern Anal. Mach. Intell. 21(9), 884–900 (1999).CrossRefGoogle Scholar
Rozo, L., Jiménez, P. and Torras, C., “Force-Based Robot Learning of Pouring Skills Using Parametric Hidden Markov Models,” 2013 9th Workshop on Robot Motion and Control (RoMoCo), Poland (IEEE,2013) pp. 227–232.Google Scholar
Rabiner, L. R., “A tutorial on hidden markov models and selected applications in speech recognition,” Proc.IEEE 77(2), 257–286 (1989).CrossRefGoogle Scholar
Russell, S. J. and Norvig, P., Artificial Intelligence: A Modern Approach (Pearson Education Limited, Harlow, United Kingdom, 2016), chapter 15.Google Scholar
Ghahramani, Z. and Jordan, M. I., “Supervised Learning from Incomplete Data via an em Approach,” In: Advances in Neural Information Processing Systems 6 (Cowan, J. D., Tesauro, G., Alspector, J., eds) (Morgan Kaufmann, San Francisco, CA, 1994) pp. 120–127.Google Scholar
Girgin, H. and Ugur, E., “Associative Skill Memory Models,” IEEE/RSJ International Conference onIntelligent Robots and Systems (IROS) (2018) pp. 6043–6048.Google Scholar
Calinon, S., “A tutorial on task-parameterized movement learning and retrieval,” Intell. Serv. Rob. 9(1),1–29 (2016).CrossRefGoogle Scholar
Tanwani, A. K. and Calinon, S., “Learning robot manipulation tasks with task-parameterized semitied hidden semi-Markov model,” IEEE Rob. Auto. Lett. 1(1), 235–242 (2016).CrossRefGoogle Scholar