Method of processing signals within a neural network to position

Details Method of processing signals within a neural network to position Method of processing signals within a neural network to position

1993-11-19

1996-04-02

Moore, David K.

395 80, 395 84, 395903, G06F 1518, G06F 1520

Patent

active

055048412

ABSTRACT:
A signal processing method for efficiently searching an optimum solution in a neural network by including a term of a nonlinear resistance in an equation of motion and changing such nonlinear resistance periodically. According to the method, the range of absolute values of connection weights between units in the neural network is limited by the equation of motion, hence preventing a prolonged search time that may otherwise be caused by excessive extension of the search scope beyond the requisite. A plurality of patterns are previously embedded or stored in the neural network and, upon input of a predetermined key pattern, the nonlinear resistance is changed periodically to recall a pattern similar to the key pattern, whereby any desired pattern can be searched or retrieved with rapidity and facility out of the complicated patterns. A process of calculating the next position of an articulated robot corresponding to an optimum solution is repeated while periodically changing a nonlinear resistance included in another equation of the positional energy of the robot, thereby acquiring the data of the robot path up to a desired goal.

REFERENCES:
patent: 4660166 (1987-04-01), Hopfield
patent: 4752906 (1988-06-01), Kleinfeld
patent: 4852018 (1989-07-01), Grossberg et al.
patent: 4990838 (1991-02-01), Kawato et al.
patent: 5155802 (1992-10-01), Mueller et al.
patent: 5167006 (1992-11-01), Furuta et al.
patent: 5172253 (1992-12-01), Lynne
patent: 5323470 (1994-06-01), Kara et al.
"Parallel Distributed Networks for Image Smoothing and Segmentation in Analog VLSI"-Lumsdaine et al., 1989 IEEE -pp. 272-278.
Alex W. Ho and Geoffrey C. Fox; "Neural Network Near-Optimal Motion Planning for a Mobile Robot on Binary and Varied Terrains"; IEEE IROS '90; p. 593-600.
Bartlett W. Mel; "Further Explorations in Visually-Guided Reaching: Making Murphy Smarter"; IEEE Conf. on Neural Information Processing Systems; 1988; pp. 348-356.
David H. Ackley; "Associative Learning Via Inhibitory Search"; IEEE Conf. on Neural Information Processing Systems; 1988; pp. 21-28.
C. Kozakiewicz and M. Ejiri; "Neural Network Approach to Path Planning for Two Dimensional Robot Motion", IROS '91, Nov. 3-5, 1991; pp. 818-823.
C. H. Chung and K. S. Lee; "Neural Network Application to the Obstacle Avoidance Path Planning for CIN"; IROS '91, 3-5 Nov. 1991; pp. 824-828.
C. H. Chung and K. S. Lee; "Hopfield Network Application to Optimal Edge Selection"; IEEE Joint Conf. on Neural Networks; 18-21 Nov. 1991; pp. 1542-1547.
U.S. Ser. No. 08/007,589, Filing Date Jan. 22, 19934, Issued to Tani.
Proceedings of the 1990 American Control Conference, San Diego, CA, USA 23-25 May 1990 pp. 2997-3000 XP170163 M. S. Fadali et al. `Minimum-time Control of Robotic Manipulators Using a Back Propagation Neural Network`-pp. 2997-3000.
Biological Cybernetics vol. 62, No. 4, Feb. 1990, Berlin, DE pp. 275-288 XP123325 M. Kawato et al. `Trajectory Formation of Arm Movement by Cascade Neural Network Model Based on Minimum Torque-change Criterion`-pp. 275-288.
INNC 90 Paris, International Neural Network Conference, Paris, FR, 9-13 Jul. 1990 pp. 229-236 XP145275 C. R. Paraten et al. `Neurocontrol applied to Telerobotics for the Space Shuttle`-pp. 229-236.
Neural Computation, Winter 1989, USA pp. 511-521 Tsurukis A. G. et al. `Non Linear Optimization using Generalized Hopfield Networks`-pp. 511-524.
Neural Network Near-Optimal Motion Planning for a Mobile Robot on Binary and Varied Terrains, Alex W. Ho and Geoffrey C. Fox, IEEE IROS '90, pp. 593.gtoreq.600.
Further Explorations in Visually-Guided Reaching: Making Murphy Smarter, Bartlett W. Mel IEEE Conf. on Neural Information Processing Systems, 1988, pp. 348-355.
Associative Learing Via Inhibitory Search, David H. Ackley, IEEE Conf on Neural Information Processing Systems, 1988, pp. 21-28.
Neural Network Approach to Path Planning for Two Dimensional Robot Motion, C. Kozakiewicz and M. Ejri, IEEE IROS '91, pp. 818-823.
Neural Network Application To The Obstacle Avoidance Path Planning for CIM (Computer Integrated Manufacturing), C. H. Chung and K. S. Lee, IEEE IROS '91, pp. 824-828.
Hopfield Network Application to Optimal Edge Selection, C. H. Chung and K. S. Lee, IEEE Joint Conf. on Neural Networks, Nov. 18-21, 1991, pp. 1542-1547.
Jun Tani, Proposal of Chaotic Steepest Descent Method for Neural Networks and Analysis of Their Dynamics, Electronics and Communications in Japan, Part 3, vol. 75, No. 4, 1992 (Translated from Denshi Joho Tsushin Gakki Ronbubshi, vol. 74-A, No. 8, Aug. 1991, pp. 1208-1215).
Jun Tani, Proposal of Chaotic Steepest Descent Method for Neural Networks and Analysis of Their Dynamics, Denshi Joho Tsushin Gakki Ronbubshi, vol. 74-A, No. 8, Aug. 1991, pp. 1208-1215.

Affiliated with

Also associated with

Rating

Method of processing signals within a neural network to position does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method of processing signals within a neural network to position, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of processing signals within a neural network to position will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2022943