Introduction to the theory of neural computation
Introduction to the theory of neural computation
Incremental evolution of complex general behavior
Adaptive Behavior - Special issue on environment structure and behavior
Evolving mobile robots able to display collective behaviors
Artificial Life
Introduction to Evolutionary Computing
Introduction to Evolutionary Computing
Evolving visibly intelligent behavior for embedded game agents
Evolving visibly intelligent behavior for embedded game agents
Hi-index | 0.00 |
This paper evaluates the Collective Neuro-Evolution (CONE) method, comparative to a related controller design method, in a simulated multi-robot system. CONE solves collective behavior tasks, and increases task performance via facilitating behavioral specialization. Emergent specialization is guided by genotype and behavioral specialization difference metrics that regulate genotype recombination. CONE is comparatively evaluated with a similar Neuro-Evolution (NE) method in a Gathering and Collective Construction (GACC) task. This task requires a multi-robot system to gather objects of various types and then cooperatively build a structure from the gathered objects. This collective behavior task requires that robots adopt complementary and specialized behaviors in order to solve. Results indicate that CONE is appropriate for evolving collective behaviors for the GACC task, given that this task requires behavioral specialization.