Sage Journals: Discover world-class research

Abstract

The kinematic mapping x = f(θ) is generally many to one. For nonredundant manipulators, this means that there are a finite num ber of configurations (joint angles) that will place the end-effector at a target location in the workspace. These correspond to pos tures of the manipulator, and each configuration lies on a specific solution branch. It is shown that for certain classes of revolute joint regional manipulators (those with no joint limits and having almost everywhere a constant number of inverse solutions in the workspace), the input-output data can be analyzed by clustering methods in order to determine the number and location of the so lution branches. As a practical consequence, the inverse kinematic mapping can be directly approximated by applying neural network or other learning-based methods to each branch separately.

Get full access to this article

View all access options for this article.

References

Baker, D.R. 1990. Some topological problems in robotics. The Mathematical Intelligencer 12(1):66-76.

Barhen, J. , Gulati, S. , and Zak, M. 1989 (June). Neural learning of inverse kinematics for redundant manipulators in unstructured environments. IEEE Computer.

Borrel, P. 1986. Contribution a la modelisation geometrique des robots manipulateurs, application a la conception assistee par ordinateur . These d'état, USTL, Montpelier .

Burdick, J. 1988. Kinematics and design of redundant robot manipulators . Ph.D. thesis, Stanford University, Stanford, CA.

DeMers, D.E. 1993. Learning to invert many-to-one mappings. Ph.D. thesis, University of California at San Diego, La Jolla, CA.

DeMers, D.E. , and Kreutz-Delago, K.K. 1992a. Learning global direct inverse kinematicss. Advances in Neural Information Processing Systems 4, ed. J. E. Moody et al. San Mateo, CA: Morgan Kaufmann, pp. 589-594.

DeMers, D.E. , and Kreutz-Delgado, K.K. 1992b. Learning global topological properties of robot kinematic mappings for neural network based configuration control. Neural Networks for Robotics, ed. K. Goldberg , pp. 3-17.

DeMers, D.E. , and Kreutz-Delgado, K.K. 1996. Canonical parameterization of excess motor degrees of freedom with self-organizing maps. IEEE Trans. Neural Networks 7(1).

Duda, R.O. , and Hart, P.E. 1973. Pattern Classification and Scene Analysis. New York: Wiley.

10.

Hsu, M.-S. , and Kohli, D. 1987. Boundary surfaces and accessibility regions for regional structure of manipulators. Mech. Mach. Theory 22(3):277-289.

11.

Jordan, M.I. , and Rumelhart, D.E. 1992 (September). Forward models: Supervised learning with a distal teacher. Cognitive Science 16:307-354.

12.

Kohli, D. , and Hsu, M.-S. 1987. The Jacobian analysis of workspaces of mechanical manipulators . Mech. Mach. Theory 22(3):265-275.

13.

Kuperstein, M. 1987 (Raleigh, NC). Adaptive visual-motor coordination in multijoint robots using parallel architecture. Proc. 1987 Int. Conf. Robotics and Automation, pp. 1595-1602.

14.

Kuperstein, M. 1988. Neural model of adaptive hand-eye coordination for single postures. Science 239:1308-1311.

15.

Kuperstein, M. 1991. INFANT neural controller for adaptive sensory-motor control . Neural Networks 4:131-145.

16.

Martinetz, T.M. , Ritter, H.J. , and Schulten, K.J. 1990. Three-dimensional neural networks for learning visuomotor coordination of a robot arm. IEEE Trans. Neural Networks 1(1):131-136.

17.

Pieper, D.L. 1968. The kinematics of manipulators under computer control . Ph.D. thesis, Stanford University, Stanford, CA.

18.

Raghavan, M. , and Roth, B. 1989 (Tokyo, Japan). Kinematic analysis of the 6R manipulator of general geometry. Proc. 5th Int. Symp. Robotics Research.

19.

Ritter, H.J. , Martinetz, T.M. , and Schulten, K.J. 1989. Topology-conserving maps for learning visuo-motor-coordination . Neural Networks 2:159-168.

20.

Spanos, J. , and Kohli, D. 1985. Workspace analysis of regional structures. J. Mech. Trans. Automation Design 107:216-223.

21.

Wenger, P. 1991. New results on the kinematics of robots: Generalizations of the aspects and classification of robots geometry. Technical Report 91.21 , Laboratoire d'Automatique de Nantes, École Centrale Nantes.

22.

Wenger, P. 1992. On the kinematics of manipulators with general geometry: Application to the feasibility analysis of continuous trajectories. Robotics and Manufacturing, vol. 4, ed. M. Jamshidi et al. New York: ASME Press, pp. 15-20.

23.

Zahn, C.T. 1971. Graph-theoretical methods for detecting and describing gestalt clusters. IEEE Trans. Comp. 20:68-86.

Learning Global Properties of Nonredundant Kinematic Mappings

Abstract

Get full access to this article

References