Multiple self-organizing maps to facilitate the learning of visuo-motor correlations

Buessler, Jean-Luc; Kara, Reda; Wira, Patrice; Kihl, H.; Urban, Jean-Philippe

doi:10.1109/icsmc.1999.823250

Cited by 10 publications

(9 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The presented results complement previous work [Buessler et al, 1999]. The robotic task was expressed in terms of visual servoing and neural learning concerned the Jacobian relationships of the visuo-motor transformation.…”

Section: Current Worksupporting

confidence: 78%

See 1 more Smart Citation

Modular Neural Architectures for Robotics

Buessler¹,

Urban²

2003

Biologically Inspired Robot Behavior Engineering

View full text Add to dashboard Cite

Abstract:The learning of sensory-motor functions have motivated important research works that emphasize a major demand: the combination of multiple neural networks to implement complex functions. A review of a number of works presents some implementations in robotics, describing the purpose of the modular architecture, its structure, and the learning technique that was applied. The second part of the chapter presents an original approach to this problem of network training, proposed by our group. Based on a bi-directional architecture, multiple networks can be trained online with simple local learning rules, while the robotic systems interact with their environment.

show abstract

Section: Current Worksupporting

confidence: 78%

“…In a previous work [Buessler et al, 1999], we analyzed the decomposition into two modules whose structure is depicted in figure 16. This architecture is briefly described, and then a complementary decomposition of modules A and B is proposed.…”

Section: Neuro-controller Architecturesmentioning

confidence: 99%

Modular Neural Architectures for Robotics

Buessler¹,

Urban²

2003

Biologically Inspired Robot Behavior Engineering

View full text Add to dashboard Cite

show abstract

“…The control signal to be delivered to the robot is computed from the weight vector of the neuron with highest value of and the matrix as follows: (12) where…”

Section: ) Delivery Of Control Signalsmentioning

confidence: 99%

“…Barreto Such properties can reduce considerably the computational load involved in robot programming, which is an item responsible for up to one-third of the total cost of implementation of an industrial robotic system [3]. Many self-organizing neural networks (SONNs) have been proposed in order to learn, for example, inverse kinematics and dynamics [4]- [12]. This is accomplished by allowing the robot arm to execute random movements within its workspace and measuring the sensory consequences.…”

Section: Introductionmentioning

confidence: 99%

A distributed robotic control system based on a temporal self-organizing neural network

Barreto

Araújo

Dücker³

et al. 2002

IEEE Trans. Syst., Man, Cybern. C

View full text Add to dashboard Cite

A distributed robot control system is proposed based on a temporal self-organizing neural network, called competitive and temporal Hebbian (CTH) network. The CTH network can learn and recall complex trajectories by means of two sets of synaptic weights, namely, competitive feedforward weights that encode the individual states of the trajectory and Hebbian lateral weights that encode the temporal order of trajectory states. Complex trajectories contain repeated or shared states which are responsible for ambiguities that occur during trajectory reproduction. Temporal context information are used to resolve such uncertainties. Furthermore, the CTH network saves memory space by maintaining only a single copy of each repeated/shared state of a trajectory and a redundancy mechanism improves the robustness of the network against noise and faults. The distributed control scheme is evaluated in point-to-point trajectory control tasks using a PUMA 560 robot. The performance of the control system is discussed and compared with other unsupervised and supervised neural network approaches. We also discuss the issues of stability and convergence of feedforward and lateral learning schemes.

show abstract

“…Several approaches can be used to determine the model of such a system [4]. In this work, we propose to use a neuromimetic approach, based on extended kohonen maps [11], [1], [5].…”

Section: Introductionmentioning

confidence: 99%

Bi-directional Modularity to Learn Visual Servoing Tasks

Hermann

Wira

Urban

2006

The 2006 IEEE International Joint Conference on Neural Network Proceedings

Self Cite

View full text Add to dashboard Cite

Abstract-This paper shows the advantage of using neural network modularity over conventional learning schemes to approximate complex functions. Indeed, it is difficult for artificial neural networks like Kohonen extended maps to converge toward an efficient and adequate solution when the dimensionality of the input and output spaces are high. Associated to an appropriate learning technique, modularity in neural networks is able to overcome the high dimensionality of the input/input space by decomposing it into different intermediate spaces of reduced dimensionality. The decomposition results in independent neural modules. The efficiency of this learning technique will be enlightened with a visual servoing application. In this application, the relationship between the visual features issued from a stereoscopic vision system and the angles of a 5 DOF-robot will be learned and approximated. Simulations have been conducted and clearly show that this complex, nonlinear, and high dimensional function can be learned efficiently with the neural network modularity approach. Moreover, we show through these simulations that neural modules can be reutilized, thus reducing the convergence time of the learning and the memory requirements.

show abstract

Multiple self-organizing maps to facilitate the learning of visuo-motor correlations

Cited by 10 publications

References 4 publications

Modular Neural Architectures for Robotics

Modular Neural Architectures for Robotics

A distributed robotic control system based on a temporal self-organizing neural network

Bi-directional Modularity to Learn Visual Servoing Tasks

Contact Info

Product

Resources

About