The University of Sussex

Analysing recurrent dynamical networks evolved for robot control

P. Husbands, I. Harvey, D. Cliff

This paper shows how a mixture of qualitative and quantitative analysis can be used to understand a particular brand of arbitrarily recurrent continuous dynamical neural network used to generate robust behaviours in autonomous mobile robots. These networks have been evolved in an open-ended way using an extended form of genetic algorithm. After briefly covering the background to our research, properties of special frequently occurring subnetworks are analysed mathematically. Networks evolved to control simple robots with low resolution sensing are then analysed using a combination of knowledge of these mathematical properties and careful interpretation of time plots of sensor, neuron and motor activities.


Download compressed postscript file