Evolution of neural controllers for locomotion and obstacle-avoidance in a 6-legged robot

Abstract : This article describes how the SGOCE paradigm has been used within the context of a "minimal simulation" strategy to evolve neural networks controlling locomotion and obstacle-avoidance in a 6-legged robot. A standard genetic algorithm has been used to evolve developmental programs according to which recurrent networks of leaky-integrators neurons were grown in a user-provided developmental substrate and were connected to the robot's sensors and actuators. Specific grammars have been used to limit the complexity of the developmental programs and of the corresponding neural controllers. Such controllers have been first evolved through simulation and then successfully downloaded on the real robot.
Document type :
Journal articles
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01021228
Contributor : David Filliat <>
Submitted on : Wednesday, July 9, 2014 - 10:24:10 AM
Last modification on : Tuesday, May 14, 2019 - 10:11:06 AM
Long-term archiving on : Thursday, October 9, 2014 - 11:27:23 AM

File

Filliat_CS99.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01021228, version 1

Citation

David Filliat, J. Kodjabachian, J.-A. Meyer. Evolution of neural controllers for locomotion and obstacle-avoidance in a 6-legged robot. Connection Science, Taylor & Francis, 1999, 11, pp.223--240. ⟨hal-01021228⟩

Share

Metrics

Record views

175

Files downloads

121