Learning Forward Models for the Operational Space Control of Redundant Robots

  • Camille Salaün
  • Vincent Padois
  • Olivier Sigaud

Abstract

We present an adaptive control approach combining model learning methods with the operational space control approach. We learn the forward kinematics model of a robot and use standard algebraic methods to extract pseudo-inverses and projectors from it. This combination endows the robot with the ability to realize hierarchically organised learned tasks in parallel, using tasks null space projectors built upon the learned models. We illustrate the proposed method on a simulated 3 degrees of freedom planar robot. This system is used as a benchmark to compare our method to an alternative approach based on learning an inverse of the extended Jacobian. We show the better versatility of the retained approach with respect to the latter.

Keywords

learning redundancy robotics inverse velocity kinematics 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Ahmad, Z., Guez, A.: On the solution to the inverse kinematic problem. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), vol. 3, pp. 1692–1697 (1990)Google Scholar
  2. Atkeson, C.: Using locally weighted regression for robot learning. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), vol. 2, pp. 958–963 (1991)Google Scholar
  3. Baillieul, J.: Kinematic programming alternatives for redundant manipulators. In: Proceedings of the International Conference on Robotics and Automation (ICRA), vol. 2, pp. 722–728 (1985)Google Scholar
  4. Barhen, J., Gulati, S., Zak, M.: Neutral learning of constrained nonlinear transformations. Computer 22(6), 67–76 (1989)CrossRefGoogle Scholar
  5. Barthelemy, S., Bidaud, P.: Stability measure of postural dynamic equilibrium based on residual radius. In: Proceedings of the 17th CISM-IFToMM Symposium on Robot Design, Dynamics and Control (RoManSy), Tokyo, Japan (2008)Google Scholar
  6. Ben Israel, A., Greville, T.: Generalized Inverses: Theory and Applications, 2nd edn. Springer, Heidelberg (2003)MATHGoogle Scholar
  7. Boudreau, R., Darenfed, S., Gosselin, C.: On the computation of the direct kinematics of parallel manipulators using polynomial networks. IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans 28(2), 213–220 (1998)CrossRefGoogle Scholar
  8. Brüwer, M., Cruse, H.: A network model for the control of the movement of a redundant manipulator. Biological Cybernetics 62(6), 549–555 (1990)CrossRefGoogle Scholar
  9. Butz, M.V., Herbort, O.: Context-dependent predictions and cognitive arm control with XCSF. In: Proceedings of the 10th annual conference on Genetic and evolutionary computation, pp. 1357–1364. ACM, New York (2008)CrossRefGoogle Scholar
  10. Calinon, S., Guenter, F., Billard, A.: On Learning, Representing and Generalizing a Task in a Humanoid Robot. IEEE Transactions on Systems, Man and Cybernetics, Part B 37(2), 286–298 (2007)CrossRefGoogle Scholar
  11. Chiaverini, S.: Singularity-robust task-priority redundancy resolution for real-time kinematic control of robot manipulators. IEEE Transactions on Robotics and Automation 13(3), 398–410 (1997)CrossRefGoogle Scholar
  12. DeMers, D., Kreutz-Delgado, K.: Inverse kinematics of dextrous manipulators. Neural Systems for Robotics, 75–116 (1997)Google Scholar
  13. Doty, K., Melchiorri, C., Bonivento, C.: A theory of generalized inverses applied to Robotics. The International Journal of Robotics Research 12(1), 1–19 (1993)CrossRefGoogle Scholar
  14. D’Souza, A., Vijayakumar, S., Schaal, S.: Learning inverse kinematics. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), vol. 1, pp. 298–303 (2001), doi:10.1109/IROS.2001.973374Google Scholar
  15. Golub, G., Van Loan, C.: Matrix computations, 3rd edn. The John Hopkins University Press, Baltimore (1996)MATHGoogle Scholar
  16. Guez, A., Ahmad, Z.: Solution to the inverse kinematics problem in robotics by neural networks. In: Proceedings of the IEEE International Conference on Neural Networks, vol. 2, pp. 617–624 (1988)Google Scholar
  17. Jordan, M.I., Rumelhart, D.E.: Forward models: Supervised learning with a distal teacher. Cognitive science 16(3), 307–354 (1992)CrossRefGoogle Scholar
  18. Khatib, O.: Dynamic control of manipulators in operational space. In: Sixth CISM-IFToMM Congress on Theory of Machines and Mechanisms, pp. 1128–1131 (1983)Google Scholar
  19. Khatib, O.: A unified approach to motion and force control of robot manipulators: The operational space formulation. IEEE Journal on Robotics and Automation 3(1), 43–53 (1987)CrossRefGoogle Scholar
  20. Klanke, S., Vijayakumar, S., Schaal, S.: A library for locally weighted projection regression. Journal of Machine Learning Research 9, 623–626 (2008)MathSciNetGoogle Scholar
  21. Kohonen, T.: Self-Organizing Maps. Springer, Berlin (2001)MATHGoogle Scholar
  22. Lee, S., Kil, R.: Robot kinematic control based on bidirectional mapping neural network. In: Proceedings of International Joint Conference on Neural Networks (IJCNN), vol. 3, pp. 327–335 (1990)Google Scholar
  23. Liégeois, A.: Automatic supervisory control of the configuration and behavior of multibody mechanisms. IEEE Transactions on Systems, Man and Cybernetics 7(12), 868–871 (1977)MATHCrossRefGoogle Scholar
  24. Ljung, L.: System identification: theory for the user. Prentice-Hall, Inc., Upper Saddle River (1986)Google Scholar
  25. Maciejewski, A., Klein, C.: Obstacle avoidance for kinematically redundant manipulators in dynamically varying environments. The International Journal of Robotics Research 4(3), 109–117 (1985)CrossRefGoogle Scholar
  26. Mansard, N., Chaumette, F.: Task sequencing for sensor-based control. IEEE Transactions on Robotics 23(1), 60–72 (2007)CrossRefGoogle Scholar
  27. Martinetz, T., Bitter, H., Schulten, K.: Learning of Visuomotor-Coordination of a robot arm with redundant degrees of freedom. In: Proceedings of the Third International Symposium on Robotics and Manufacturing–Research, Education, and Applications, Amer. Society of Mechanical, p. 521 (1990)Google Scholar
  28. Martinetz, T., Ritter, H., Schulten, K.: Three-dimensional neural net for learning visuomotor coordination of a robot arm. IEEE Transactions on Neural Networks 1(1), 131–136 (1990)CrossRefGoogle Scholar
  29. Metta, G., Sandini, G., Vernon, D., Natale, L., Nori, F.: The iCub humanoid robot: an open platform for research in embodied cognition. In: PerMIS: Performance Metrics for Intelligent Systems Workshop, Washington DC, USA (2008)Google Scholar
  30. Nakamura, Y.: Advanced Robotics: redundancy and optimization. Addison Wesley, Reading (1991)Google Scholar
  31. Nakanishi, J., Cory, R., Mistry, M., Peters, J., Schaal, S.: Operational space control: A theoretical and empirical comparison. The International Journal of Robotics Research 27(6), 737–757 (2008)CrossRefGoogle Scholar
  32. Natale, L., Nori, F., Metta, G., Sandini, G.: Learning precise 3d reaching in a humanoid robot. In: Proceedings of the IEEE International Conference of Development and Learning (ICDL), London, UK, pp. 1–6 (2007)Google Scholar
  33. Nguyen, L., Patel, R., Khorasani, K.: Neural network architectures for the forward kinematics problem in robotics. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN), vol. 3, pp. 393–399 (1990)Google Scholar
  34. Nguyen-Tuong, D., Peters, J., Seeger, M., Schoelkopf, B.: Learning inverse dynamics: a comparison. In: Proceedings of the European Symposium on Artificial Neural Networks, ESANN (2008)Google Scholar
  35. Nguyen-Tuong, D., Seeger, M., Peters, J.: Real-time local gp model learning. In: Sigaud, O., Peters, J. (eds.) From Motor Learning to Interaction Learning in Robots. SCI, vol. 264, pp. 193–207. Springer, Heidelberg (2010)Google Scholar
  36. Peters, J., Schaal, S.: Learning to control in operational space. The International Journal of Robotics Research 27(2), 197–212 (2008)CrossRefGoogle Scholar
  37. Pourboghrat, F.: Neural networks for learning inverse-kinematics of redundant manipulators. In: Proceedings of the 32nd Midwest Symposium on Circuits and Systems, vol. 2, pp. 760–762 (1989)Google Scholar
  38. Rojas, R.: Neural networks: a systematic introduction. Springer, Heidelberg (1996)Google Scholar
  39. Sadjadian, H., Taghirad, H.D.: Numerical methods for computing the forward kinematics of a redundant parallel manipulator. In: Proceedings of the IEEE Conference on Mechatronics and Robotics, Aachen, Germany (2004)Google Scholar
  40. Sang, L.H., Han, M.C.: The estimation for forward kinematic solution of stewart platform using the neural network. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), vol. 1, pp. 501–506 (1999)Google Scholar
  41. Schaal, S., Atkeson, C.G.: Receptive field weighted regression. ART Human Inf. Process Lab, Kyoto, Japan, Tech. Rep. TR-H-209 (1997)Google Scholar
  42. Schaal, S., Atkeson, C.G., Vijayakumar, S.: Scalable techniques from nonparametric statistics for real time robot learning. Applied Intelligence 17(1), 49–60 (2002)MATHCrossRefGoogle Scholar
  43. Sentis, L., Khatib, O.: Synthesis of whole-body behaviors through hierarchical control of behavioral primitives. The International Journal of Humanoid Robotics 2(4), 505–518 (2005)CrossRefGoogle Scholar
  44. Shon, A., Grochow, K., Rao, R.: Robotic imitation from human motion capture using gaussian processes. In: Proceedings of the IEEE-RAS/RSJ International Conference on Humanoid Robots, Humanoids (2005)Google Scholar
  45. Van der Smagt, P.P.: Minimisation methods for training feedforward neural networks. Neural Networks 7(1), 1–11 (1994)CrossRefGoogle Scholar
  46. Snyman, J.A.: Practical mathematical optimization: an introduction to basic optimization theory and classical and new gradient-based algorithms. Springer, Heidelberg (2005)MATHGoogle Scholar
  47. Sun, G., Scassellati, B.: Reaching through learned forward model. In: 4th IEEE/RAS International Conference on Humanoid Robots, vol. 1, pp. 93–112 (2004)Google Scholar
  48. Sun, G., Scassellati, B.: A fast and efficient model for learning to reach. International Journal of Humanoid Robotics 2(4), 391–414 (2005)CrossRefGoogle Scholar
  49. Toussaint, M., Goerick, C.: A bayesian view on motor control and planning. In: Sigaud, O., Peters, J. (eds.) From Motor Learning to Interaction Learning in Robots. SCI, vol. 264, pp. 227–252. Springer, Heidelberg (2010)Google Scholar
  50. Vijayakumar, S., Schaal, S.: Locally weighted projection regression: An o (n) algorithm for incremental real time learning in high dimensional space. In: Proceedings of the Seventeenth International Conference on Machine Learning (ICML 2000), Stanford, CA (2000)Google Scholar
  51. Vijayakumar, S., D’Souza, A., Schaal, S.: LWPR: A Scalable Method for Incremental Online Learning in High Dimensions. Tech. rep. Edinburgh University Press (2005)Google Scholar
  52. Walter, J., Schulten, K.: Implementation of self-organizing neural networks for visuo-motor control of an industrial robot. IEEE Transactions on Neural Networks 4(1), 86–96 (1993)CrossRefGoogle Scholar
  53. Wang, D., Zilouchian, A.: Solutions of kinematics of robot manipulators using a kohonen self-organizing neural network. In: Proceedings of the IEEE International Symposium on Intelligent Control, pp. 251–255 (1997)Google Scholar
  54. Willow, G.: Overview of the PR2 robot (2009), http://www.willowgarage.com/pages/robots/pr2-overview

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Camille Salaün
    • 1
  • Vincent Padois
    • 1
  • Olivier Sigaud
    • 1
  1. 1.Institut des Systèmes Intelligents et de Robotique - CNRS UMR 7222Université Pierre et Marie CurieParis CEDEX 5France

Personalised recommendations