A neural network for robot control: Cooperation between neural units as a requirement for learning
Computers & Electrical EngineeringPublished 1 July 1993
Thomas Martinetz, Klaus Schulten
Citations15
SJR quartileQ1
SJR score1.05
SNIP1.63
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
The results of a simulation and a mathematical analysis of the learning procedure show that cooperation between neural units during the course of learning, incorporated in the network, is essential for the robot arm system to succeed in learning.
Abstract
Abstract We present a self-organizing neural network for learning visuo-motor coordination and describe its application to the task of learning the end effector positioning of a simulated, three-jointed robot arm. In contrast to a neural network algorithm that we introduced earlier in Refs we now employ visual feedback which enables the robot arm to position its end effector with an accuracy of about 5% of the size of the workspace after only 100 learning steps and with a final accuracy of about 0.06% after 6000 learning steps. Learning proceeds without the need for an external teacher by a sequence of trial movements using input signals from a pair of cameras. The use of visual feedback enables the robot arm not only to adapt to slowly occurring miscalibrations, but also to compensate for sudden changes in its geometry, e.g. when picking up a tool. The results of a simulation and a mathematical analysis of the learning procedure show that cooperation between neural units during the course of learning, incorporated in the network, is essential for the robot arm system to succeed in learning.
Keywords
Computer ScienceNeuroscienceEngineering
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.
Springer series in information sciencesSelf-Organization and Associative Memory
8,770 Citations1989Teuvo Kohonen
Proceedings of the Royal Society of London. Series B, Biological sciencesHow patterned neural connections can be set up by self-organization
834 Citations1976David Willshaw, C. von der Malsburg
Without needing to make any elaborate assumptions about its structure or about the operations its elements are to carry out, it is shown that the mappings are set up in a system- to-system rather than a cell-to-cell fashion.
ScienceMultiple Representations of the Body Within the Primary Somatosensory Cortex of Primates
727 Citations1979Jon H. Kaas, Randall J. Nelson +3 more
Microelectrode mapping experiments indicate that the classical primary somatosensory cortex of monkeys consists of as many as four separate body representations rather than just one.
Annual Review of NeuroscienceThe Reorganization of Somatosensory Cortex Following Peripheral Nerve Damage in Adult and Developing Mammals
659 Citations1983J. H. Kaas, M. M. Merzenich +1 more
Artificial IntelligenceIntelligent control
400 Citations1993Barbara Hayes‐Roth
In my 1985 paper, “A Blackboard Architecture for Control” [7], I claimed that the control problem is fundamental to all cognitive processes and intelligent systems.
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.
Biological CyberneticsOn the stationary state of Kohonen's self-organizing sensory mapping
293 Citations1986Helge Ritter, Klaus Schulten
The stationary state of the self-organizing sensory mapping of Kohonen is investigated and the equation for the stationary state is derived for the case of one-dimensional and two-dimensional mappings.
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 Neural NetworksThree-dimensional neural net for learning visuomotor coordination of a robot arm
261 Citations1990Thomas Martinetz, Helge Ritter +1 more
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.
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.
Proceedings of the National Academy of SciencesHow to label nerve cells so that they can interconnect in an ordered fashion.
175 Citations1977C. von der Malsburg, David Willshaw
A method for setting up topographically ordered mappings between two sheets of nerve cells by inducing a set of chemical markers that express the neighborhood relationships within the presynaptic sheet is presented.
Biological CyberneticsFormation of topographic maps and columnar microstructures in nerve fields
142 Citations1979A. Takeuchi, Шун-ичи Амари
A mathematical analysis of a revised version of the Willshaw-Malburg model of topographic formation, solving the equations of synaptic self-organization coupled with the field equation of neural excitations proves that two cases exist depending on parameters, and that the smooth topographic organization is obtained as a stable equilibrium of the equations.
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.
IEEE International Conference on Neural NetworksA neural controller for collision-free movement of general robot manipulators
51 Citations1988Graf, LaLonde
An approach is presented for the collision-free control of general robot manipulators moving among a changing set of obstacles, which combines neural and systolic computing principles and extends previous work on neural manipulator control.
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.
Biological CyberneticsThe Extended Branch-Arrow Model of the formation of retino-tectal connections
35 Citations1982Kenneth J. Overton, Michael A. Arbib
XBAM (the Extended Branch-Arrow Model), a new model of the development of the retino-tectal topographic mapping as observed in frog, toad, and goldfish visual systems, is presented.
Handbook of sensory physiologyProjection of Optic Pathways to the Visual Cortex
32 Citations1973D. Whitteridge
The topographical representation of the retina on the visual receptive surfaces to be found in the lateral geniculate nucleus, superior colliculus and visual cortex is incomprehensible without some knowledge of the distribution of receptors and ganglion cells in the retina.
Hierarchical neural net for learning control of a robot's arm and gripper
29 Citations1990Thomas Martinetz, Klaus Schulten
A hierarchical neural network structure capable of learning the control of a robot's arm and gripper is introduced and, due to cooperation between neighboring neurons during the training phase, fewer than two trial movements per neuron were sufficient to learn the required control 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.