Supplanting neural networks with ODEs in evolutionary robotics

Authors:
Paul Grouchy;Gabriele M. T. D'Eleuterio
Affiliations:
University of Toronto Institute for Aerospace Studies, Toronto, Ontario, Canada;University of Toronto Institute for Aerospace Studies, Toronto, Ontario, Canada
Venue:
SEAL'10 Proceedings of the 8th international conference on Simulated evolution and learning
Year:
2010

Citing 5
Cited 0

Evolving neural networks through augmenting topologies

Evolutionary Computation
Evolution and Development of a Multicellular Organism: Scalability, Resilience, and Neutral Complexification

Artificial Life
Compositional pattern producing networks: A novel abstraction of development

Genetic Programming and Evolvable Machines
A Field Guide to Genetic Programming

A Field Guide to Genetic Programming
A coarse-coding framework for a gene-regulatory-based artificial neural tissue

ECAL'05 Proceedings of the 8th European conference on Advances in Artificial Life

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new approach to evolutionary robotics is presented. Neural networks are abstracted and supplanted by a system of ordinary differential equations that govern the changes in controller outputs. The equations are evolved as trees using an evolutionary algorithm based on symbolic regression in genetic programming. Initial proof-of-concept experiments are performed using a simulated two-wheeled robot that must drive a straight line while wheel response properties vary. Evolved controllers demonstrate the ability to learn and adapt to a changing environment, as well as the ability to generalize and perform well in novel situations.