UCT CS Research Document Archive

The Evolution of Evolvability in Evolutionary Robotics

Shorten, David and Geoff Nitschke (2016) The Evolution of Evolvability in Evolutionary Robotics. In Proceedings 15th International Conference on the Synthesis and Simulation of Living Systems (ALIFE VX), pages 260-267, Cancun, Mexico.

Full text available as:
PDF - Requires Adobe Acrobat Reader or other PDF viewer.

Abstract

Previous research has demonstrated that computational models of Gene Regulatory Networks (GRNs) can adapt so as to increase their evolvability, where evolvability is defined as a population’s responsiveness to environmental change. In such previous work, phenotypes have been represented as bit strings formed by concatenating the activations of the GRN after simulation. This research is an extension where previous results supporting the evolvability of GRNs are replicated, however, the phenotype space is enriched with time and space dynamics with an evolutionary robotics task environment. It was found that a GRN encoding used in the evolution of a way-point navigation behavior in a fluctuating environment results in (robot controller) populations becoming significantly more responsive (evolvable) over time. This is as compared to a direct encoding of controllers which was unable to improve it’s evolvability in the same task environment.

EPrint Type:Conference Paper
Subjects:I Computing Methodologies: I.2 ARTIFICIAL INTELLIGENCE
ID Code:1192
Deposited By:Nitschke, Geoff
Deposited On:23 November 2017