Three-dimensional neural net for learning visuomotor coordination of a robot arm
IEEE Transactions on Neural NetworksPublished 1 March 1990
Thomas Martinetz, Helge Ritter, Klaus Schulten
Citations261
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
An extension of T. Kohonen's (1982) self-organizing mapping algorithm together with an error-correction scheme based on the Widrow-Hoff learning rule is applied to develop a learning algorithm for the visuomotor coordination of a simulated robot arm.
Abstract
An extension of T. Kohonen's (1982) self-organizing mapping algorithm together with an error-correction scheme based on the Widrow-Hoff learning rule is applied to develop a learning algorithm for the visuomotor coordination of a simulated robot arm. Learning occurs by a sequence of trial movements without the need for an external teacher. Using input signals from a pair of cameras, the closed robot arm system is able to reduce its positioning error to about 0.3% of the linear dimensions of its work space. This is achieved by choosing the connectivity of a three-dimensional lattice consisting of the units of the neural net.
Keywords
Computer ScienceNeuroscienceEngineering
NatureLearning representations by back-propagating errors
30,885 Citations1986David E. Rumelhart, Geoffrey E. Hinton +1 more
Back-propagation repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector, which helps to represent important features of the task domain.
Biological CyberneticsSelf-organized formation of topologically correct feature maps
9,519 Citations1982Teuvo Kohonen
In a simple network of adaptive physical elements which receives signals from a primary event space, the signal representations are automatically mapped onto a set of output responses in such a way that the responses acquire the same topological order as that of the primary events.
ScienceNeuronal Population Coding of Movement Direction
3,216 Citations1986Apostolos P. Georgopoulos, Andrew B. Schwartz +1 more
The direction of movement was found to be uniquely predicted by the action of a population of motor cortical neurons that can be monitored during various tasks, and similar measures in other neuronal populations could be of heuristic value where there is a neural representation of variables with vectorial attributes.
Boston studies in the philosophy of scienceContour Enhancement, Short Term Memory, and Constancies in Reverberating Neural Networks
650 Citations1982Stephen Grossberg
It is suggested that competition solves a sensitivity problem that confronts all cellular systems: the noise-saturation dilemma.
Studies in Applied MathematicsContour Enhancement, Short Term Memory, and Constancies in Reverberating Neural Networks
630 Citations1973Stephen Grossberg
A model of the nonlinear dynamics of reverberating on-center off-surround networks of nerve cells, or of cell populations, is analysed and applications to seizure and hallucinatory phenomena, to position codes for mo~or control, to pattern discrimination, to influences of novel events on storage of redundant relevant cues, and to the construction of a sensory-drive heterarchy are mentioned.
Comprehensive physiologyPerceptual Structures and Distributed Motor Control
569 Citations1981Michael A. Arbib
Biological CyberneticsAnalysis of a simple self-organizing process
471 Citations1982Teuvo Kohonen
An analysis of two partial processes of a recently discovered self-organizing process where a set of numerical representations assumes the correct order and the final map of the representations converges to its asymptotic form.
ScienceNeural Model of Adaptive Hand-Eye Coordination for Single Postures
344 Citations1988Michael Kuperstein
A neural network model has been developed that achieves adaptive visual-motor coordination of a multijoint arm, without a teacher, that is designed to be generalized for coordinating any number of topographic sensory inputs with limbs ofAny number of joints.
Neural NetworksTopology-conserving maps for learning visuo-motor-coordination
265 Citations1989Helge Ritter, Thomas Martinetz +1 more
It is shown that both arm kinematics and arm dynamics can be learned, if a suitable representation for the map output is used, due to the topology-conserving property of the map spatially neighboring neurons can learn cooperatively.
IEEE Transactions on Systems Man and CyberneticsReal-time application of neural networks for sensor-based control of robots with vision
234 Citations1989Wallace T. Miller
A practical neural network-based learning control system is described that is applicable to complex robotic systems involving multiple feedback sensors and multiple command variables.
Trends in NeurosciencesSensory and motor maps in the mammalian superior colliculus
178 Citations1987David L. Sparks, Ion S. Nelson
Converging lines of evidence indicate that the superior colliculus is an important part of the neural substrate for the generation oforienting responses, involved in both the localization of sensory stimuli and the initiation of orienting responses.
Adaptive visual-motor coordination in multijoint robots using parallel architecture
95 Citations2005Michael Kuperstein
This article derives and simulates a neural-like network architecture that adaptively controls a visually guided, two-jointed robot arm to reach spot targets in three dimensions.
IEEE Control Systems MagazineImplementation of an adaptive neural controller for sensory-motor coordination
67 Citations1989Michael Kuperstein, Jacob Rubenstein
A theory and the prototype of a neural controller called INFANT that learns sensory-motor coordination from its own experience and relies on the self-consistency between sensory and motor signals to achieve unsupervised learning are presented.
AIP conference proceedingsTopology conserving mappings for learning motor tasks
46 Citations1986Helge Ritter, Klaus Schulten
Topology conserving mappings play an important role for biological processing of sensory input and principles found capable of establishing such maps can also be applied to organize the learning of motor tasks.
A neural network computational map approach to reflexive motor control
9 Citations2003Stephen H. Lane, David A. Handelman +1 more
Using the neural basis of human motor control as a guide, it was possible to develop a control strategy based on the localized structure of reflex arcs, antagonistic actuation, and the encoding of movement by neuronal populations.