Neural Network Control of a Pneumatic Robot Arm

A neural map algorithm has been employed to control a five-joint pneumatic robot arm and gripper through feedback from two video cameras. The pneumatically driven robot arm (SoftArm) employed in this investigation shares essential mechanical characteristics with skeletal muscle systems. To control the position of the arm, 200 neurons formed a network representing the three-dimensional workspace embedded in a four-dimensional system of coordinates from the two cameras, and learned a three-dimensional set of pressures corresponding to the end effector positions, as well as a set of 3/spl times/4 Jacobian matrices for interpolating between these positions. The gripper orientation was achieved through adaptation of a 1/spl times/4 Jacobian matrix for a fourth joint. Because of the properties of the rubber-tube actuators of the SoftArm, the position as a function of supplied pressure is nonlinear, nonseparable, and exhibits hysteresis. Nevertheless, through the neural network learning algorithm the position could be controlled to an accuracy of about one pixel (/spl sim/3 mm) after 200 learning steps and the orientation could be controlled to two pixels after 800 learning steps. This was achieved through employment of a linear correction algorithm using the Jacobian matrices mentioned above. Applications of repeated corrections in each positioning and grasping step leads to a very robust control algorithm since the Jacobians learned by the network have to satisfy the weak requirement that the Jacobian yields a reduction of the distance between gripper and target. The neural network employed in the control of the SoftArm bears close analogies to a network which successfully models visual brain maps. It is concluded, therefore, from this fact and from the close analogy between the SoftArm and natural muscle systems that the successful solution of the control problem has implications for biological visuo-motor control. >

[1]  C. Malsburg,et al.  How patterned neural connections can be set up by self-organization , 1976, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[2]  Roman Bek,et al.  Discourse on one way in which a quantum-mechanics language on the classical logical base can be built up , 1978, Kybernetika.

[3]  G. Blasdel,et al.  Voltage-sensitive dyes reveal a modular organization in monkey striate cortex , 1986, Nature.

[4]  John J. Craig,et al.  Introduction to Robotics Mechanics and Control , 1986 .

[5]  Klaus Schulten,et al.  Topology-conserving maps for learning visuo-motor-coordination , 1989, Neural Networks.

[6]  M. Kuperstein,et al.  Implementation of an adaptive neural controller for sensory-motor coordination , 1989, International 1989 Joint Conference on Neural Networks.

[7]  Masazumi Katayama,et al.  Learning Trajectory and Force Control of an Artificial Muscle Arm , 1990, NIPS.

[8]  Helge J. Ritter,et al.  Three-dimensional neural net for learning visuomotor coordination of a robot arm , 1990, IEEE Trans. Neural Networks.

[9]  Klaus Schulten,et al.  A Comparison between a Neural Network Model for the Formation of Brain Maps and Experimental Data , 1991, NIPS.

[10]  MICHAEL KUPERSTEIN,et al.  INFANT neural controller for adaptive sensory-motor coordination , 1991, Neural Networks.

[11]  Evangelos E. Milios,et al.  Adaptive neural networks for vision-guided position control of a robot arm , 1992, Proceedings of the 1992 IEEE International Symposium on Intelligent Control.

[12]  G. Blasdel,et al.  Orientation selectivity, preference, and continuity in monkey striate cortex , 1992, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[13]  Helge J. Ritter,et al.  Neural computation and self-organizing maps - an introduction , 1992, Computation and neural systems series.

[14]  Klaus Schulten,et al.  Implementation of self-organizing neural networks for visuo-motor control of an industrial robot , 1993, IEEE Trans. Neural Networks.