Article ID Journal Published Year Pages File Type
493723 Swarm and Evolutionary Computation 2012 14 Pages PDF
Abstract

This article comparatively tests three cooperative co-evolution methods for automated controller design in simulated robot teams. Collective Neuro-Evolution (CONE) co-evolves multiple robot controllers using emergent behavioral specialization in order to increase collective behavior task performance. CONE is comparatively evaluated with two related controller design methods in a collective construction task. The task requires robots to gather building blocks and assemble the blocks in specific sequences in order to build structures. Results indicate that for the team sizes tested, CONE yields a higher collective behavior task performance (comparative to related methods) as a consequence of its capability to evolve specialized behaviors.

► This article presents the Collective Neuro-Evolution (CONE) method. ► CONE uses cooperative co-evolution to automate controller design in simulated robot teams. ► CONE evolves collective behaviors using emergent behavioral specialization as a problem solver. ► CONE is comparatively tested with related methods in a collective construction task. ► CONE’s capability to evolve specialized behaviors allows it to out-perform related methods.

Related Topics
Physical Sciences and Engineering Computer Science Computer Science (General)
Authors
, , ,