### Abstract

The problems of controlling a plant while avoiding obstacles and experiencing perturbations in the plants dynamics are considered. It is assumed that the plant's dynamics is not known in advance. To solve this problem a self-organizing artificial neural network (ANN) solution is advanced here. The ANN consists of various parts. The first part discretizes the state space of the plant and also learns the geometry of the state space. The learnt geometrical relations are represented by lateral connections. These connections are utilized for planning a speed field, allowing collision free motion. The speed field is defined over the neural representation of the state space and is transformed into control signals with the help of interneuron associated with the lateral connections: connections between interneurons and control neurons encode the inverse dynamics of the plant. These connections are learnt during a direct system inverse identification process by Hebbian learning. Theoretical results and computer experiments show the robustness of approach.

Original language | English |
---|---|

Pages (from-to) | 875-896 |

Number of pages | 22 |

Journal | Neural Network World |

Volume | 6 |

Issue number | 6 |

Publication status | Published - 1996 |

### Fingerprint

### ASJC Scopus subject areas

- Software

### Cite this

*Neural Network World*,

*6*(6), 875-896.

**Neurocontrol I : Self-organizing speed-field tracking.** / Szepesvari, Csaba; Lőrincz, A.

Research output: Contribution to journal › Article

*Neural Network World*, vol. 6, no. 6, pp. 875-896.

}

TY - JOUR

T1 - Neurocontrol I

T2 - Self-organizing speed-field tracking

AU - Szepesvari, Csaba

AU - Lőrincz, A.

PY - 1996

Y1 - 1996

N2 - The problems of controlling a plant while avoiding obstacles and experiencing perturbations in the plants dynamics are considered. It is assumed that the plant's dynamics is not known in advance. To solve this problem a self-organizing artificial neural network (ANN) solution is advanced here. The ANN consists of various parts. The first part discretizes the state space of the plant and also learns the geometry of the state space. The learnt geometrical relations are represented by lateral connections. These connections are utilized for planning a speed field, allowing collision free motion. The speed field is defined over the neural representation of the state space and is transformed into control signals with the help of interneuron associated with the lateral connections: connections between interneurons and control neurons encode the inverse dynamics of the plant. These connections are learnt during a direct system inverse identification process by Hebbian learning. Theoretical results and computer experiments show the robustness of approach.

AB - The problems of controlling a plant while avoiding obstacles and experiencing perturbations in the plants dynamics are considered. It is assumed that the plant's dynamics is not known in advance. To solve this problem a self-organizing artificial neural network (ANN) solution is advanced here. The ANN consists of various parts. The first part discretizes the state space of the plant and also learns the geometry of the state space. The learnt geometrical relations are represented by lateral connections. These connections are utilized for planning a speed field, allowing collision free motion. The speed field is defined over the neural representation of the state space and is transformed into control signals with the help of interneuron associated with the lateral connections: connections between interneurons and control neurons encode the inverse dynamics of the plant. These connections are learnt during a direct system inverse identification process by Hebbian learning. Theoretical results and computer experiments show the robustness of approach.

UR - http://www.scopus.com/inward/record.url?scp=0030384620&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030384620&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0030384620

VL - 6

SP - 875

EP - 896

JO - Neural Network World

JF - Neural Network World

SN - 1210-0552

IS - 6

ER -