Advertisement

Learning task manifolds for constrained object manipulation

We’re sorry, something doesn't seem to be working properly.

Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

Abstract

Reliable physical interaction is essential for many important challenges in robotic manipulation. In this paper, we consider Constrained Object Manipulations tasks (COM), i.e. tasks for which constraints are imposed on the grasped object rather than on the robot’s configuration. To enable robust physical interaction with the environment, this paper presents a manifold learning approach to encode the COM task as a vector field. This representation enables an intuitive task-consistent adaptation based on an object-level impedance controller. Simulations and experimental evaluations demonstrate the effectiveness of our approach for several typical COM tasks, including dexterous manipulation and contour following.

This is a preview of subscription content, log in to check access.

Access options

Buy single article

Instant unlimited access to the full article PDF.

US$ 39.95

Price includes VAT for USA

Subscribe to journal

Immediate online access to all issues from 2019. Subscription will auto renew annually.

US$ 99

This is the net price. Taxes to be calculated in checkout.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19

Notes

  1. 1.

    The key idea of Virtual Frame is to define an object frame only using the positions of fingertips. This definition actually ignores the rolling and slippage between the object and the fingertips.

  2. 2.

    In practice, only the contact forces on each fingertip can be measured, which include the grasping forces and the manipulating forces. The aim of the grasping forces is to keep the object stable and by definition their sum is equal to the constant external force such as the gravity of the grasped object, which is ignored in our case.

  3. 3.

    http://www.simlab.co.kr/Allegro-Hand.htm.

  4. 4.

    http://www.syntouchllc.com/.

  5. 5.

    \(\Delta x_{lim}^t\) is chosen by considering the rotation limitation of the human hand and the Allegro hand.

  6. 6.

    This moving direction is not mandatory for our approach, however it will be helpful to visualize the force pattern during demonstration.

References

  1. Berenson, D., Srinivasa, S. S., Ferguson, D., Collet, A., & Kuffner, J. J. (2009a). Manipulation planning with workspace goal regions. In IEEE International Conference on Robotics and Automation (ICRA), (pp. 618–624).

  2. Berenson, D., Srinivasa, S. S., Ferguson, D., Kuffner, & J. J. (2009b). Manipulation planning on constraint manifolds. In: IEEE International Conference on Robotics and Automation (ICRA), (pp. 625–632).

  3. Berenson, D., Srinivasa, S. S., & Kuffner, J. (2011). Task space regions: A framework for pose-constrained manipulation planning. The International Journal of Robotics Research, 30(12), 1435–1460.

  4. Buchli, J., Stulp, F., Theodorou, E., & Schaal, S. (2011). Learning variable impedance control. The International Journal of Robotics Research, 30(7), 820–833.

  5. Cheng, M. Y., & Wang, Y. H. (2009). Velocity field construction for contour following tasks represented in nurbs form. IEEE Transactions on Automatic Control, 54(10), 2405–2410.

  6. Dollar, P., Rabaud, V., Belongie, S.J. (2007). Non-isometric manifold learning: analysis and an algorithm. In Ghahramani Z (ed) ICML, ACM, ACM International Conference Proceeding Series, (Vol. 227, pp. 241–248).

  7. El-Khasawneh, B. S., & Ferreira, P. M. (1999). Computation of stiffness and stiffness bounds for parallel link manipulators. International Journal of Machine Tools and Manufacture, 39(2), 321–342.

  8. Gienger, M., Toussaint, M., Goerick, C. (2008). Task maps in humanoid robot manipulation. In 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems), IEEE, (pp. 2758–2764).

  9. Gienger, M., Toussaint, M., Goerick, C. (2010). Whole-body motion planning–building blocks for intelligent systems. In Motion Planning for Humanoid Robots, Springer, (pp. 67–98).

  10. Havoutis, I., & Ramamoorthy, S. (2013). Motion planning and reactive control on learnt skill manifolds. The International Journal of Robotics Research. doi:10.1177/0278364913482016.

  11. Huang, B., Li, M., De Souza, R. L., Bryson, J. J., & Billard, A. (2016). A modular approach to learning manipulation strategies from human demonstration. Autonomous Robots, 40(5), 903–927.

  12. Kavraki, L. E., Švestka, P., Latombe, J. C., & Overmars, M. H. (1996). Probabilistic roadmaps for path planning in high-dimensional configuration spaces. IEEE Transactions on Robotics and Automation, 12(4), 566–580.

  13. Kim, B. H., Yi, B. J., Oh, S. R., Suh, I. H. (2001a). Fundamentals and analysis of compliance characteristics for multifingered hands. In International Conference on Robotics and Automation (ICRA).

  14. Kim, B. H., Yi, B. J., Oh, S. R., Suh, I. H. (2001b). Task-based compliance planning for multifingered hands. In Proceedings of International Conference on Robotics and Automation (ICRA).

  15. Kishi, Y., Luo, Z., Asano, F., & Hosoe, S. (2003). Passive impedance control with time-varying impedance center. IEEE International Symposium on Computational Intelligence in Robotics and Automation, 3, 1207–1212.

  16. Ko, I., Kim, B., & Park, F. C. (2014). Randomized path planning on vector fields. The International Journal of Robotics Research, 33(13), 1664–1682.

  17. Kronander, K., & Billard, A. (2012). Online learning of varying stiffness through physical human-robot interaction. In International Conference on Robotics and Automation (ICRA).

  18. Krug, R., Stoyanov, T., Tincani, V., Andreasson, H., Mosberger, R., Fantoni, G., et al. (2016). The next step in robot commissioning: Autonomous picking and palletizing. IEEE Robotics and Automation Letters, 1(1), 546–553.

  19. Kuo, P. H., DeBacker, J., Deshpande, A. (2015). Design of robotic fingers with human-like passive parallel compliance. In IEEE International Conference on Robotics and Automation (ICRA), (pp. 2562–2567), doi:10.1109/ICRA.2015.7139543.

  20. Li, M., Bekiroglu, Y., Kragic, D., Billard, A. (2014a). Learning of grasp adaptation through experience and tactile sensing. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), (pp. 3339–3346).

  21. Li, M., Hang, K., Kragic, D., & Billard, A. (2016). Dexterous grasping under shape uncertainty. Robotics and Autonomous Systems, 75, 352–364.

  22. Li, P. Y., & Horowitz, R. (1999). Passive velocity field control of mechanical manipulators. IEEE Transactions on Robotics and Automation, 15(4), 751–763.

  23. Li, P. Y., & Horowitz, R. (2001a). Passive velocity field control (pvfc). Part i. Geometry and robustnessd. IEEE Transactions on Automatic Control, 46(9), 1346–1359.

  24. Li, P. Y., & Horowitz, R. (2001b). Passive velocity field control (pvfc). Part ii. Application to contour following. IEEE Transactions on Automatic Control, 46(9), 1360–1371.

  25. Li, M., Yin, H., Tahara, K., & Billard, A. (2014b). Learning object-level impedance control for robust grasping and dexterous manipulation. In IEEE International Conference on Robotics and Automation (ICRA), (pp. 6784–6791).

  26. Mason, M. T. (1981). Compliance and force control for computer controlled manipulators. IEEE Transactions on Systems, Man, and Cybernetics, 11(6), 418–432.

  27. Mussa-Ivaldi, F. A., & Giszter, S. F. (1992). Vector field approximation: A computational paradigm for motor control and learning. Biological Cybernetics, 67(6), 491–500.

  28. Okamura, A. M., Smaby, N., & Cutkosky, M. R. (2000). An overview of dexterous manipulation. IEEE International Conference on Robotics and Automation (ICRA), 1, 255–262.

  29. Oriolo, G., Ottavi, M., & Vendittelli, M. (2002). Probabilistic motion planning for redundant robots along given end-effector paths. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2, 1657–1662.

  30. Ott, C. (2008). Cartesian impedance control of redundant and flexible-joint robots. Berlin: Springer.

  31. Porta, J. M., Jaillet, L., & Bohigas, O. (2012). Randomized path planning on manifolds based on higher-dimensional continuation. The International Journal of Robotics Research, 31(2), 201–215.

  32. Rodriguez, A., Basaez, L., & Celaya, E. (2008). A relational positioning methodology for robot task specification and execution. IEEE Transactions on Robotics, 24(3), 600–611.

  33. Saitoh, Y., Luo, Z., & Watanabe, K. (2003). Adaptive modular vector field control for robot contact tasks in uncertain environment. IEEE International Conference on Systems, Man and Cybernetics, 4, 3645–3650.

  34. Schneider, S. A., & Cannon, R. H. (1992). Object impedance control for cooperative manipulation: Theory and experimental results. IEEE Transactions on Robotics and Automation, 8(3), 383–394.

  35. Shimoga, K., & Goldenberg, A. (1991). Grasp admittance center: Choosing admittance center parameters. In American Control Conference, (pp. 2527–2532).

  36. Siciliano, B., & Khatib, O. (2008). Springer handbook of robotics. Berlin: Springer.

  37. Siciliano, B., Sciavicco, L., Villani, L., & Oriolo, G. (2008). Robotics: Modelling, planning and control (1st ed.). New York: Springer.

  38. Sikka, P., & McCarragher, B. J. (1997). Stiffness-based understanding and modeling of contact tasks by human demonstration. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

  39. Sommer, N., Li, M., & Billard, A. (2014). Bimanual compliant tactile exploration for grasping unknown objects. In International Conference on Robotics and Automation (ICRA).

  40. Stilman, M. (2010). Global manipulation planning in robot joint space with task constraints. IEEE Transactions on Robotics, 26(3), 576–584.

  41. Suh, C., Um, T., Kim, B., Noh, H., Kim, M., & Park, F. (2011). Tangent space rrt: A randomized planning algorithm on constraint manifolds. In IEEE International Conference on Robotics and Automation (ICRA), (pp. 4968–4973).

  42. Tahara, K., Arimoto, S., & Yoshida, M. (2010). Dynamic object manipulation using a virtual frame by a triple soft-fingered robotic hand. In IEEE International Conference on Robotics and Automation (ICRA).

  43. Wimböck, T., Ott, C., & Hirzinger, G. (2008). Analysis and experimental evaluation of the intrinsically passive controller (IPC) for multifingered hands. In IEEE International Conference on Robotics and Automation (ICRA).

  44. Wimböck, T., Ott, C., Albu-Schäffer, A., & Hirzinger, G. (2012). Comparison of object-level grasp controllers for dynamic dexterous manipulation. The International Journal of Robotics Research, 31(1), 3–23.

  45. Yang, B. H., & Asada, H. (1996). Progressive learning and its application to robot impedance learning. IEEE Transactions on Neural Networks, 7(4), 941–952.

  46. Yao, Z., Gupta, K. (2005). Path planning with general end-effector constraints: Using task space to guide configuration space search. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), (pp. 1875–1880).

Download references

Acknowledgements

This work was supported by the European Union Seventh Framework Programme FP7/2007-2013 under Grant Agreement No. 288533 ROBOHOW.COG.

Author information

Correspondence to Miao Li.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 2 (wmv 2967 KB)

Supplementary material 1 (wmv 9826 KB)

Supplementary material 2 (wmv 2967 KB)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Li, M., Tahara, K. & Billard, A. Learning task manifolds for constrained object manipulation. Auton Robot 42, 159–174 (2018). https://doi.org/10.1007/s10514-017-9643-z

Download citation

Keywords

  • Task manifold
  • Impedance learning
  • Constrained object manipulation
  • Task-consistent adaptation