The Cost of Morphological Complexity

Furman, Alex and Nagar, Danielle and Nitschke, Geoff (2019) The Cost of Morphological Complexity, Proceedings of Genetic and Evolutionary Computation Conference (GECCO 2019), Prague, Czech Republic, 125-126, ACM.

[img] PDF
2019-The_Cost_of_Morphological_Complexity.pdf

Download (470kB)

Abstract

This study investigates the impact of imposing a cost on morphological complexity given co-adapting behavior-morphology couplings in simulated robots. Specifically, we investigate the environmental and evolutionary conditions for which morphological complexity can be evolved without sacrificing behavioral efficacy. This study evaluates the relationship between task difficulty (environment complexity) and evolved morphological complexity. We use multi-objective neuro-evolution to evolve robot controller-morphology couplings in task environments of increasing difficulty, where the objectives are to minimize the cost of (morphological) complexity and to maximize behavior quality (task performance). Results indicate that imposing a cost of complexity induces the evolution of simpler morphologies with negligible differences in behavior (task performance) across increasingly complex environments (increasing task difficulty).

Item Type: Conference poster
Subjects: Computing methodologies > Artificial intelligence
Date Deposited: 20 Sep 2019
Last Modified: 10 Oct 2019 15:31
URI: http://pubs.cs.uct.ac.za/id/eprint/1327

Actions (login required)

View Item View Item