The evolution of modular artificial neural networks for legged robot control

Authors:
Sethuraman Muthuraman;Grant Maxwell;Christopher MacLeod
Affiliations:
School of Engineering, The Robert Gordon University, Aberdeen, U.K.;School of Engineering, The Robert Gordon University, Aberdeen, U.K.;School of Engineering, The Robert Gordon University, Aberdeen, U.K.
Venue:
ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
Year:
2003

Citing 5
Cited 4

Evolution of the ancestral vertebrate brain

The handbook of brain theory and neural networks
Modular neural net systems, training of

The handbook of brain theory and neural networks
Incremental Evolution in ANNs: Neural Netswhich Grow

Artificial Intelligence Review
Automatic Generation of Neural Network Architecture Using Evolutionary Computation

Automatic Generation of Neural Network Architecture Using Evolutionary Computation
Evolutionary Artificial Neural Networks for Quadruped Locomotion

ICANN '02 Proceedings of the International Conference on Artificial Neural Networks

Modular neural networks with Hebbian learning rule

Neurocomputing
Incremental growth in modular neural networks

Engineering Applications of Artificial Intelligence
Evolutionary algorithms for real-time artificial neural network training

ICANN'05 Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications - Volume Part II
Investigation of efficient features for image recognition by neural networks

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper outlines a system that allows a neural network, which is used to control a robot, to evolve in a structured but open-ended way. The final intention of the research is that, as the network develops, intelligence will eventually emerge. This is accomplished by placing the robot in a developing environment and allowing both this environment and the robot's body form, sensors and actuators to become more complex and sophisticated as time passes. As this development takes place, neural network modules are added to the control system. The result is that the robot's complexity and that of the neural network grows with its environment. Results are presented showing the system in operation on a simulated legged robot.