A formulation for collision identification and distance calculation in motion planning using neural networks

  • Z. Dong
  • J. Yuan
Article

Abstract

The collision identification and object-to-object distance calculation play an important role in the motion planning for robots and manufacturing facilities. A formulation for collision identification and distance calculation in motion planning, using neural networks, is presented. The method calculates the distances between the vertices of an object and the given polyhedral obstacles using the modified Hamming net. This formulation is derived from the homogeneous geometric transformations. The method can be used to identify collision between the vertices of a moving object and the obstacles, to calculate the distance and interference between the moving object and the obstracle, and to find the optimal direction for collision removal. The parallel computation formulation is simple in form, and can be extended to line-to-object and object-to-object collision identification and distance calculation. The method can considerably decrease required computation time, and has the potential for being applied to on-line trajectory planning.

Keywords

Collision, identification Distance calculation Motion planning Neural networks Robotics 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    J. E. Bobrow, “A direct minimization approach for obtaining the distance between convex polyhedrons”,The International Journal of Robotics Research,8 (3), pp. 65–76, June 1989.Google Scholar
  2. 2.
    C. Y. Liu and R. W. Mayne, “Distance calculations in motion planning problems with interference situations”,Proceedings of the 1990 ASME Design and Technology Conference DE-Vol 23-1, pp. 145–152, 1990.Google Scholar
  3. 3.
    T. Lozano-Perez and M. A. Wesley, “An algorithm for planning collision-free paths among polyhedral obstacles”,Communications of the ACM,22 (10), pp. 560–570, October 1979.Google Scholar
  4. 4.
    C. Y. Liu and R. W. Mayne, “Nonlinear optimization in collision free trajectory planning and geometric design”,SME Transactions on Robotics Research, V. 1, pp. 6.11–6.48, 1990.Google Scholar
  5. 5.
    W. E. Red, “Minimum distance for robot task simulation”,Robotica, V. 1, pp. 231–238, 1983.Google Scholar
  6. 6.
    E. G. Gilbert and D. W. John, “Distance functions and their application to robot path planning in the presence of obstacles”,IEEE Journal of Robotics and Automation,RA-1 (1), pp. 21–30, 1985.Google Scholar
  7. 7.
    C. E. Buckley, “A foundation for the ‘flexible-trajectory’ approach to numeric path planning”,The International Journal of Robotics Research,8 (3), pp. 44–64, 1989.Google Scholar
  8. 8.
    R. O. Buchal, D. B. Cherchas, F. Sassani and J. P. Duncan, 1989, “Simulated off-line programming of welding robots”,The International Journal of Robotics Research,8 (3), pp. 31–43, 1979.Google Scholar
  9. 9.
    J. W. Boyse, “Interference detection among solid and surfaces”,Communications of ACM,22 (1), pp. 3–9, January 1979.Google Scholar
  10. 10.
    M. A. Ganter and J. J. Uicker, “Dynamic collision detection using swept solid”,Journal of Mechanisms Transmissions, and Automation in Design,108, pp. 549–555, 1986.Google Scholar
  11. 11.
    M. C. Leu, S. H. Park and K. K. Wang, “Geometric representation of translational swept volumes and its applications”,Journal of Engineering for Industry,108, pp. 113–119, 1986.Google Scholar
  12. 12.
    W. P. Wang and K. K. Wang, “Geometric modeling for swept volume of moving solids”,IEEE Computer Graphics and Applications, pp. 8–17, 1986.Google Scholar
  13. 13.
    C. Y. Liu, W. R. Chen and R. W. Mayne, “An approach to dynamic distance calculations for obstacle avoidance problems”,Proceedings of the 1991 ASME Design and Technology Conference DE 33-3, pp. 1–7, 1991.Google Scholar
  14. 14.
    J. D. Weld and M. C. Leu, “Geometric respresentation of swept volumes with application to polyhedral objects”,The International Journal of Robotics Research,9 (5), pp. 105–117, October 1990.Google Scholar
  15. 15.
    D. E. Rumelhart, G. E. Hinton and R. J. Williams, “Learning internal representations by error propagation”,Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1: Foundations, MIT Press, 1986.Google Scholar
  16. 16.
    B. Widrow and R. Winter, “Neural net for adaptive filtering and adaptive pattern recognition”,IEEE Computer Magazine, pp. 25–39, March 1988.Google Scholar
  17. 17.
    R. P. Lippmann, “An introduction to computing with neural net”,IEEE ASSP Magazine, pp. 4–22, April 1987.Google Scholar
  18. 18.
    J. J. Hopfield, “Neural networks and physical systems with emergent collective computational abilities”,Proceedings of the National Academy of Sciences, USA,79, pp. 2554–2558, April 1982.Google Scholar
  19. 19.
    H. Yao, Z. Dong and R. Podhorodeski, “Simulation of range finding devices by geometric modelling”,Computers in Enginering 1991, vol. 1, ASME, pp. 327–332, 1991.Google Scholar
  20. 20.
    H. Yao, R. Podhorodeski and Z. Dong, “An approach to generate geometric models for multiple range images”, Technical Paper 92-4-1, University of Victoria, 1992.Google Scholar

Copyright information

© Springer-Verlag London Limited 1993

Authors and Affiliations

  • Z. Dong
    • 1
  • J. Yuan
    • 1
  1. 1.Department of Mechanical EngineeringUniversity of VictoriaVictoriaCanada

Personalised recommendations