Patent
1994-09-15
1997-09-30
Downs, Robert W.
G06F 1518
Patent
active
056733674
ABSTRACT:
A method of motion control for robotics and other automatically controlled machinery using a neural network controller with real-time environmental feedback. The method is illustrated with a two-finger robotic hand having proximity sensors and force sensors that provide environmental feedback signals. The neural network controller is taught to control the robotic hand through training sets using back- propagation methods. The training sets are created by recording the control signals and the feedback signal as the robotic hand or a simulation of the robotic hand is moved through a representative grasping motion. The data recorded is divided into discrete increments of time and the feedback data is shifted out of phase with the control signal data so that the feedback signal data lag one time increment behind the control signal data. The modified data is presented to the neural network controller as a training set. The time lag introduced into the data allows the neural network controller to account for the temporal component of the robotic motion. Thus trained, the neural network controlled robotic hand is able to grasp a wide variety of different objects by generalizing from the training sets.
REFERENCES:
patent: 4541771 (1985-09-01), Beni et al.
patent: 4682805 (1987-07-01), Reynolds
patent: 4730861 (1988-03-01), Spencer
patent: 4766322 (1988-08-01), Hashimoto
patent: 4850631 (1989-07-01), Dotsko
patent: 4852018 (1989-07-01), Grossberg et al.
patent: 4884216 (1989-11-01), Kuperstein
patent: 4990838 (1991-02-01), Kawato et al.
patent: 5063492 (1991-11-01), Yoda et al.
patent: 5113482 (1992-05-01), Lynne
patent: 5124918 (1992-06-01), Beer et al.
patent: 5136687 (1992-08-01), Edelamn et al.
patent: 5253329 (1993-10-01), Villarreal et al.
patent: 5259064 (1993-11-01), Furuta et al.
patent: 5355435 (1994-10-01), DeYong et al.
patent: 5371834 (1994-12-01), Tawel
patent: 5420964 (1995-05-01), Sugasaka et al.
Eisley, A learning architecture for control based on back-propagation neural networks, IEEE International conference on neural networks, pp. 587-594 Jul. 27, 1988.
Kozakiewicz et al., Calibration analysis of a direct drive robot, IEEE International workshop on intelligent robots and systems, pp. 213-220 Jul. 6, 1990.
Yee et al., Network for Kinematics problem in parallel manipulator, 1991 IEEE International conference on neural networks, pp. 1699-1704 Nov. 21, 1991.
Pourboghart., Neural networks for learning Inverse-Kinematicsof redundant Manipulators, Proceedings on the 32nd midwest symposium on circuits and systems, pp. 760-762 Aug. 16, 1989.
Chen et al., Learning control with neural networks, Proceedings: 1989 International conference on robotics and automation, pp. 1448-1453 May 19, 1989.
Yeung et al., Using a context sensitive learning network for robot arm control, Proceedings of the 1989 International conference on robotics and automation, pp. 1441-1447 May 19, 1989.
Kirchner et al., A perturbation approach to robot calibration, International Journal of robotics research, pp. 47-60 1987.
Josin et al., Robot control using neural network, ICNN, pp. 635-631 Jul. 27, 1988.
Kozakiewicz et al., Partitioned neural network architecture for Inverse Kinematics calculation of a 6 dof robot manipulator, IEEE International joint conference on neural network, pp. 2001-2006 Nov. 21, 1991.
Takanashi, 6 d.o.f. manipulators absolute positioning accuracy improvement using a neural network proceedings of the 1990 IEEE International workshop on intelligent robots and systems, pp. 635-640 Jul. 6, 1990.
Guez et al., Solution to the inverse kinematics problem in robotics by neural networks, IEEE International conference on neural network, pp. 617-624 Jul. 28, 1988.
Kuromatsu et al., Autonomous trajectory generation of a biped locomotive robot, 1991 IEEE International joint conference on neural networks, pp. 1983-1988 Nov. 21, 1991.
Bullock et al., A self-organizing neural network model for redundant sensory-motor control, motor equivalence, and tool use, IJCNN International joint conference on neural networks, pp. 91-96 Jun. 11,1992.
Gardner et al., Applications of neural network for trajectory control of robots, %th International conference on advanced robotics, pp. 487-492, vol. 1 Jun. 22, 1991.
S. Srinivasan, Robert E. Gander, and Hugh C. Wood; "A Movement Pattern Generator Model Using Artificial Neural Networks"; Biomedical Engineering; Ju. 1992; pp. 716-722.
Roselle Anderson and Adarsh Bhat; "Virtual Reality MindGames and Sense Alteration"; Stanford Star; May 1992; p. 8.
Cecilia Tom; "Bionic Limb Technology may be a Decade Away"; The Stanford Weekly; Jul. 19, 1990; p. 5.
Maureen Caudill; Naturally Intelligent Systems; 1990, pp. 250-255.
William F. Allman; Apprentices of Wonder; 1989, pp. 136-137.
Gardner et al, "Applications of Neural Networks for Trajectory Control of Robots", 5th Int'l Conf on Advanced Robotics, Jun. 19-22, 1991, pp. 487-492 vol. 1.
Buckley, "Neural Network Motion Control Status", Aug. 4, 1989.
Buckley, "Neural Network Motion Control Example", Aug. 25, 1989.
Elsley, "A Learning Architecture for Control Based on Back-Propagation Neural Networks", IEEE Inter Conf on Neural Networks, Jul. 24-27, 1988, pp. 587-594.
Kuperstein et al, "Neural Controller for Adaptive Movements with Unforseen Payloads", IEEE Transactions on Neural Networks vol. 1 No. 1 Mar. 1990, pp. 137-142.
Downs Robert W.
Leary James J.
Shah Sanjiv
LandOfFree
Method for neural network control of motion using real-time envi 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 for neural network control of motion using real-time envi, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for neural network control of motion using real-time envi will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2263169