Journal of Intelligent & Robotic Systems

, Volume 77, Issue 1, pp 17–35 | Cite as

Model Predictive Motion Control based on Generalized Dynamical Movement Primitives

Article

Abstract

In this work, experimental data is used to estimate the free parameters of dynamical systems intended to model motion profiles for a robotic system. The corresponding regression problem is formed as a constrained non-linear least squares problem. In our method, motions are generated via embedded optimization by combining dynamical movement primitives in a locally optimal way at each time step. Based on this concept, we introduce a model predictive control scheme which allows generalization over multiple encoded behaviors depending on the current position in the state space, while leveraging the ability to explicitly account for state constraints to the fulfillment of additional tasks such as obstacle avoidance. We present a numerical evaluation of our approach and a preliminary verification by generating grasping motions for the anthropomorphic Shadow Robot hand/arm platform.

Keywords

Motion Control Model Predictive Control Motion Planning Imitation Learning Grasping 

Mathematics Subject Classifications (2010)

70E60 68T40 68T05 93C10 49M99 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Hwang, J.H., Arkin, R., Kwon, D.S.: Mobile robots at your fingertip: Bezier curve on-line trajectory generation for supervisory control. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, Vol. 2, 2003, pp. 1444–1449Google Scholar
  2. 2.
    Aleotti, J., Caselli, S.: Robust trajectory learning and approximation for robot programming by demonstration. Robot. Auton. Syst. 54(5), 409–413 (2006)CrossRefGoogle Scholar
  3. 3.
    Schittkowski, K.: Numerical Data Fitting in Dynamical Systems. Kluwer Academic Publishers (2002)Google Scholar
  4. 4.
    Billard, A., Calinon, S., Dillmann, R., Schaal, S.: Robot programming by demonstration. In: Siciliano, B., Khatib, O. (eds.) Handbook of Robotics, pp 1371–1394. Springer (2008)Google Scholar
  5. 5.
    Flash, T., Hogans, N.: The coordination of arm movements: an experimentally confirmed mathematical model. J. Neurosci. 5, 1688–1703 (1985)Google Scholar
  6. 6.
    Weitschat, R., Haddadin, S., Huber, F., Albu-Schauffer, A.: Dynamic optimality in real-time: a learning framework for near-optimal robot motions. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 5636–5643 (2013)Google Scholar
  7. 7.
    Khansari-Zadeh, S.M., Billard, A.: A dynamical system approach to realtime obstacle avoidance. Auton. Robot. 32(4), 433–454 (2012)CrossRefGoogle Scholar
  8. 8.
    Khatib, O.: Real-time obstacle avoidance for manipulators and mobile robots. IJRR 5(1), 90–98 (1986)MathSciNetGoogle Scholar
  9. 9.
    Feix, T., Pawlik, R., Schmiedmayer, H., Romero, J., Kragic, D.: A comprehensive grasp taxonomy. In: RSS: Workshop on Understanding the Human Hand for Advancing Robotic Manipulation (2009)Google Scholar
  10. 10.
    Shadow Robot Company, The shadow dextrous hand. [Online]. Available: http://www.shadowrobot.com/hand/
  11. 11.
    Bernardino, A., Henriques, M., Hendrich, N., Zhang, J.: Precision grasp synergies for dexterous robotic hands. In: Proceedings of the IEEE International Conference on Robotics and Biomimetics, pp. 62–67 (2013)Google Scholar
  12. 12.
    Ijspeert, A.J., Nakanishi, J., Schaal, S.: Learning attractor landscapes for learning motor primitives. In: Advances in Neural Information Processing Systems. MIT Press (2003)Google Scholar
  13. 13.
    Ude, A., Gams, A., Asfour, T., Morimoto, J.: Task-specific generalization of discrete and periodic dynamic movement primitives. IEEE Trans. Robot. 26(5), 800–815 (2010)CrossRefGoogle Scholar
  14. 14.
    Khansari-Zadeh, S., Billard, A.: Learning stable nonlinear dynamical systems with gaussian mixture models. IEEE Trans. Robot. 27(5), 943–957 (2011)CrossRefGoogle Scholar
  15. 15.
    Forte, D., Gams, A., Morimoto, J., Ude, A.: On-line motion synthesis and adaptation using a trajectory database. Robot. Auton. Syst. 60(10), 1327–1339 (2012)CrossRefGoogle Scholar
  16. 16.
    Krug, R., Dimitrov, D.: Representing movement primitives as implicit dynamical systems learned from multiple demonstrations. In: Proceedings of the International Conference on Advanced Robotics, pp. 1–8 (2013)Google Scholar
  17. 17.
    Ijspeert, A., Nakanishi, J., Pastor, P., Hoffmann, H., Schaal, S.: Dynamical movement primitives: learning attractor models for motor behaviors. Neural Comput. 25, 328–373 (2013)CrossRefMATHMathSciNetGoogle Scholar
  18. 18.
    Kormushev, P., Calinon, S., Caldwell, D.: Robot motor skill coordination with em-based reinforcement learning. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 3232–3237 (2010)Google Scholar
  19. 19.
    Stulp, F., Schaal, S.: Hierarchical reinforcement learning with movement primitives. In: 11th IEEE-RAS International Conference on Humanoid Robots, 231–238 (2011)Google Scholar
  20. 20.
    Stulp, F., Theodorou, E., Buchli, J., Schaal, S.: Learning to grasp under uncertainty. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 5703–5708 (2011)Google Scholar
  21. 21.
    Kober, J, Peters, J.: Policy search for motor primitives in robotics. Mach. Learn. 84(1-2), 171–203 (2011)CrossRefMATHMathSciNetGoogle Scholar
  22. 22.
    Nemec, B., Vuga, R., Ude, A.: Efficient sensorimotor learning from multiple demonstrations. Adv. Robot. 27(13), 1023–1031 (2013)CrossRefGoogle Scholar
  23. 23.
    Pastor, P., Hoffmann, H., Asfour, T., Schaal, S.: Learning and generalization of motor skills by learning from demonstration. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 763–768 (2009)Google Scholar
  24. 24.
    Matsubara, T., Hyon, S., Morimoto, J.: Learning stylistic dynamic movement primitives from multiple demonstrations. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 1277–1283 (2010)Google Scholar
  25. 25.
    Calinon, S., Li, Z., Alizadeh, T., Tsagarakis, N., Caldwell, D.: Statistical dynamical systems for skills acquisition in humanoids. In: IEEE-RAS International Conference on Humanoid Robots, 323–329 (2012)Google Scholar
  26. 26.
    Muelling, K., Kober, J., Kroemer, O., Peters, J.: Learning to select and generalize striking movements in robot table tennis. IIJR 3, 263–279 (2013)Google Scholar
  27. 27.
    Gribovskaya, E., Khansari-Zadeh, S.M., Billard, A.: Learning non-linear multivariate dynamics of motion in robotic manipulators. IJRR 30(1), 80–117 (2011)Google Scholar
  28. 28.
    Hoffmann, H., Pastor, P., Park, D.-H., Schaal, S.: Biologically-inspired dynamical systems for movement generation: automatic real-time goal adaptation and obstacle avoidance. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 2587–2592 (2009)Google Scholar
  29. 29.
    Gams, A., Nemec, B., Zlajpah, L., Wachter, M., Ijspeert, A., Asfour, T., Ude, A.: Modulation of motor primitives using force feedback: interaction with the environment and bimanual tasks. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 5629–5635 (2013)Google Scholar
  30. 30.
    Saveriano, M., Lee, D.: Point cloud based dynamical system modulation for reactive avoidance of convex and concave obstacles. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 5380–5387 (2013)Google Scholar
  31. 31.
    Raković, S.V., Mayne, D.Q.: Robust model predictive control for obstacle avoidance: discrete time case. In: Assessment and Future Directions of Nonlinear Model Predictive Control, pp 617–627. Springer (2007)Google Scholar
  32. 32.
    Shiller, Z., Sharma, S., Stern, I., Stern, A.: Online obstacle avoidance at high speeds. IJRR 32(9–10), 1030–1047 (2013)Google Scholar
  33. 33.
    Pecora, F., Cirillo, M., Dimitrov, D.: On mission-dependent coordination of multiple vehicles under spatial and temporal constraints. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 5262– 5269 (2012)Google Scholar
  34. 34.
    Anderson, S., Karumanchi, S., Iagnemma, K.: Constraint-based planning and control for safe, semi-autonomous operation of vehicles. In: IEEE Intelligent Vehicles Symposium, pp. 383–388 (2012)Google Scholar
  35. 35.
    Wangmanaopituk, H.V.S., Kongprawechnon, W.: Collaborative nonlinear model-predictive motion planning and control of mobile transport robots for a highly flexible production system. Science Asia (2010)Google Scholar
  36. 36.
    Da Silva, M., Abe, Y., Popović, J.: Simulation of human motion data using short-horizon model-predictive control. Comput. Graph. Forum. 27(2), 371–380 (2008)CrossRefGoogle Scholar
  37. 37.
    Khalil, H.: Nonlinear Systems. Prentice Hall (2002)Google Scholar
  38. 38.
    Rückert, E., d’Avella, A.: Learned parametrized dynamic movement primitives with shared synergies for controlling robotic and musculoskeletal systems. Front. comput. Neurosci. 7 (2013)Google Scholar
  39. 39.
    Mayne, D.Q., Rawlings, J.B., Rao, C.V., Scokaert, P.O.: Constrained model predictive control: stability and optimality. Automatica 36(6), 789–814 (2000)CrossRefMATHMathSciNetGoogle Scholar
  40. 40.
    Houska, B., Ferreau, H., Diehl, M.: ACADO Toolkit – an open source framework for automatic control and dynamic optimization. Opt. Control Appl. Methods 32(3), 298–312 (2011)CrossRefMATHMathSciNetGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2014

Authors and Affiliations

  1. 1.AASS Research CenterÖrebro UniversityÖrebroSweden
  2. 2.INRIASt IsmierFrance

Personalised recommendations