Evolving neuro-modules and their interfaces to control autonomous robots
Bruno Lara, Martin Hülse, and Frank Pasemann
Contact the author: Please use for correspondence this email.
Submission date: 20. Apr. 2001
published in: Proceedings of the 5th world multiconference on systemics, cybernetics and informatics : SCI/ISAS 2001 ; July 22-25, 2001, Orlando, Florida
Orlando, FL : The Institute, 2001. - P. 259 - 264
with the following different title: Evolving different neuro-modules and their interfaces to control autonomous robots
Download full preprint: PDF (305 kB), PS ziped (233 kB)
An evolutionary algorithm for the creation of recurrent network structures is presented. The aim is to develop neural networks controlling the behaviour of miniature robots. Two neuro-modules are created separately using this evolutionary approach. The first neuro-module gives the agents the ability to move within an environment without colliding with obstacles. The second neuro-module provides the agents with a phototropic behaviour. The interaction of the neuro-modules is then investigated evolving the necessary interface to provide the agents with a coherent obstacle avoidance and phototropic behaviour. The evolution process is carried out in a simulated environment and individuals with high performance are also tested on a physical environment with the use of Khepera robots.