Skip to main content

Advertisement

Springer Nature Link
Log in

Perception-based learning for motion in contact in task planning

  • Published:
Journal of Intelligent and Robotic Systems Aims and scope Submit manuscript

Abstract

This paper presents a new approach to error detection during motion in contact under uncertainty for robotic manufacturing tasks. In this approach, artificial neural networks are used for perception-based learning. The six force-and-torque signals from the wrist sensor of a robot arm are fed into the network. A self-organizing map is what learns the different contact states in an unsupervised way. The method is intended to work properly in complex real-world manufacturing environments, for which existent approaches based on geometric analytical models may not be feasible, or may be too difficult. It is used for different tasks involving motion in contact, particularly the peg-in-hole insertion task, and complex insertion or extraction operations in a flexible manufacturing system. Several real examples for these cases are presented.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Asada, H.: Representation and learning of nonlinear compliance using neural nets, IEEE Trans. Robotics and Automation 9(6) (1993), 863–867.

    Google Scholar 

  2. Bekey, G. A. and Ghosal, A. (eds): Neural Networks in Robotics, Kluwer Academic Publishers, Dordrecht, 1992.

    Google Scholar 

  3. Brokowski, M. A., Peshkin, M. A., and Goldberg, K.: Curved fences for part alignment, in Proc. IEEE Int. Conf. Robotics and Automation, 1993, pp. 467–473.

  4. Brost, R. C.: Dynamic analysis of planar manipulation tasks, in Proc. IEEE Int. Conf. Robotics and Automation, 1992, pp. 2247–2254.

  5. Buckley, S. J.: Planning compliant motion strategies, Int. J. Robotics Res. 8(5) (1989), 28–44.

    Google Scholar 

  6. Canny, J. and Reif, J.: New lower bound techniques for robot motion planning problems, in Proc. 28th IEEE Symp. Foundation of Computer Science, Los Angeles, 1987, pp. 49–60.

  7. Cervera, E. and del Pobil, A. P.: A hybrid qualitative—connectionist approach to robotic spatial planning, in Proc. Workshop on Spatial and Temporal Reasoning, Int. Joint Conf. on Artificial Intelligence (IJCAI-95), Montreal, Canada, 1995, pp. 37–46.

  8. Cervera, E. and del Pobil, A. P.: Geometric reasoning for fine motion planning, in Proc. IEEE Int. Symp. Assembly and Task Planning, Pittsburgh, PA, 1995, pp. 154–159.

  9. Cervera, E. and delPobil, A. P.: Multiple self-organizing maps for supervised learning, in J.Mira and F.Sandoval (eds), From Natural to Artificial Neural Computation, Springer, Berlin, 1995, pp. 345–352.

    Google Scholar 

  10. Cervera, E., del Pobil, A. P., Marta, E., and Serna, M. A.: A sensor-based approach for motion in contact in task planning, in Proc. IEEE/RSJ Int. Conf. Intell. Robots and Systems (IROS '95), Pittsburgh, PA, Vol. 2, 1995, pp. 468–473.

  11. Cervera, E., delPobil, A. P., Marta, E., and Serna, M. A.: Dealing with uncertainty in fine motion: A neural approach, in G. F.Forsyth and A.Ali (eds), Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, Gordon and Breach, Amsterdam, 1995, pp. 119–126.

    Google Scholar 

  12. Chaar, J. K., Volz, R. A., and Davidson, E. S.: An integrated approach to developing manufacturing control software, in Proc. IEEE Int. Conf. Robotics and Automation, 1991, pp. 1979–1984.

  13. Chen, N. and Hwang, C.: Robot path planner: A neural networks approach, Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems, 1992.

  14. Dakin, G. A. and Popplestone, R. J.: Augmenting a nominal assembly motion plan with a compliant behavior, Proc. Natl. Conf. Artificial Intelligence, 1991.

  15. delPobil, A. P. and Serna, M. A.: Spatial Representation and Motion Planning, Springer, Berlin, 1995.

    Google Scholar 

  16. Desai, R. J. and Volz, R. A.: Identification and verification of termination conditions in fine motion in presence of sensor erros and geometric uncertainties, in Proc. IEEE Int. Conf. Robotics and Automation, 1989, pp. 800–805.

  17. Donald, B. R.: A geometric approach to error detection and recovery for robot motion planning with uncertainty, Artif. Intell. 37 (1988), 223–271.

    Google Scholar 

  18. Gini, M., et al.: The role of knowledge in the architecture of robust robot control, in Proc. IEEE Int. Conf. Robotics and Automation, 1985, pp. 561–567.

  19. Goldberg, K.: Orienting polygonal parts without sensors, Algorithmica (Aug. 1993).

  20. Goldberg, K. and Mason, M. T.: Bayesian grasping, Proc. IEEE Int. Conf. Robotics and Automation, May 1990.

  21. Gottschlich, S. and Kak, A. C.: A dynamic approach to high-precision parts mating, IEEE Trans. Systems, Man and Cybernetics (1989), 19.

  22. Gullapalli, V., Franklin, J. A., and Benbrahim, H.: Acquiring robot skills via reinforcement learning, IEEE Control Systems 14(1) (1994), 13–24.

    Google Scholar 

  23. Hertz, J. A., Krogh, A., and Palmer, R. G.: Introduction to the Theory of Neural Computation, Addison-Wesley, Reading, MA, 1991.

    Google Scholar 

  24. Kohonen, T.: The self-organizing map, Proc. IEEE 78, (1190), 1464–1480.

    Google Scholar 

  25. Kohonen, T.: Self-Organizing Maps, Springer Series in Information Sciences, 1995.

  26. Kumaradjaja, R. and DiCesare, F.: A causal reasoning approach for planning error recovery in automated manufacturing systems, in Proc. SPIE Symp. Advances Intelligent Robotic Systems Expert Robots for Industrial Use, 1988, pp. 144–153.

  27. Kung, S. Y. and Hwang, J. N.: Neura networks architectures for robotic applications, IEEE Trans. Robotics and Automation 5(5) (1989), 641–657.

    Google Scholar 

  28. Lee, L. H. and Bien, Z.: Collision-free trajectory control for multiple robots based on neural optimization network, Robotica 8 (1990), 185–194.

    Google Scholar 

  29. Lozano-Pérez, T., Mason, M. T., and Taylor, R. H.: Automatic synthesis of fine-motion strategies for robots, Int. J. Robotics Res. 3(1) (1984), 3–24.

    Google Scholar 

  30. Martin, P. and del Pobil, A. P.: A connectionist system for learning robot manipulator obstacleavoidance capabilities in path-planning, Proc. IMACS Int. Symp. on Signal Processing, Robotics and Neural Networks, Lille, France, April 1994.

  31. Martin, P. and del Pobil, A. P.: Application of artificial neural networks to the robot path planning problem, in G. Rzevski, D. W. Russell and R. A. Adey (eds), Applications of Artificial Intelligence in Engineering, Vol. IX, Computational Mechanics Publications, 1994, pp. 73–80.

  32. Millán, J. and Torras, C.: A reinforcement connectionist approach to robot path-finding in no-maze-like environments, Machine Learning 8 (1992), 363–395.

    Google Scholar 

  33. Natarajan, B. K.: The complexity of fine motion planning, Tech. Rept. TR-86-734, Department of Computer Science, Cornell University, 1986.

  34. Park, J. and Lee, S.: Neural computation for collision-free path planning, in Proc. IEEE Conf. Neural Networks, Vol. 2, 1990, pp. 229–232.

  35. Peshkin, M. A.: Programmed compliance for error corrective assembly, IEEE Trans. Robotics and Automation 6 (1990), 473–482.

    Google Scholar 

  36. Rao, A. and Goldberg, K.: Shape from diameter; recognizing polygonal parts with a paralleljaw gripper, Int. J. Robotics Res. (Spring 1993).

  37. Su, S. F. and Lee, C. S. G.: Manipulation and propagation of uncetainty and verification of applicability of actions in assembly tasks, IEEE Trans. Systems, Man, and Cybernetics SMC-22(6) (Nov./Dec. 1992), 1376–1389.

    Google Scholar 

  38. Taylor, G. and Taylor, P.: Dynamic error probability vectors: A framework for sensory decision making, in Proc. IEE Int. Conf. Robotics Automation, 1988, pp. 1096–1100.

  39. Torras, C.: From geometric motion planning to neural motor control in robotics, Al Comm. 6(1) (1993), 3–17.

    Google Scholar 

  40. Xiao, J. and Volz, R. A.: On replanning for assembly tasks using robots in the presence of uncertainties, in Proc. IEEE Int. Conf. Robotics and Automation, 1989, pp. 638–645.

Download references

Author information

Authors and Affiliations

  1. Computer Science Department, Jaume I University, Campus Penyeta Roja, E-12071, Castelló, Spain

    Enrique Cervera & Angel P. Del Pobil

  2. Robotics and Al Laboratory, C.E.I.T., Manuel de Lardizábal, 13-15, E-20009, San Sebastián, Spain

    Edward Marta & Miguel A. Serna

  3. University of Navarra, Manuel de Lardizábal, 13-15, E-20009, San Sebastián, Spain

    Edward Marta & Miguel A. Serna

Authors
  1. Enrique Cervera
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Angel P. Del Pobil
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Edward Marta
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Miguel A. Serna
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

Category: (8) AI in Robotics and Manufacturing/FMS.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Cervera, E., Del Pobil, A.P., Marta, E. et al. Perception-based learning for motion in contact in task planning. Journal of Intelligent and Robotic Systems 17, 283–308 (1996). https://doi.org/10.1007/BF00339665

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00339665

Key words