DocumentCode :
2815619
Title :
Behavioral heterogeneity, cooperation, and collective construction
Author :
Nitschke, Geoff
Author_Institution :
Interdiscipl. Studies Dept., Univ. of Tokyo, Tokyo, Japan
fYear :
2012
fDate :
10-15 June 2012
Firstpage :
1
Lastpage :
8
Abstract :
This paper evaluates two Neuro-Evolution (NE) methods to adapt controllers in simulated robot teams. The first method evolves controllers with fixed topologies and adapts team size as a function of task complexity. The second method evolves controller topology as a function of task complexity, but keeps team sizes constant. These methods are: Collective Neuro-Evolution 2 (CONE-2), and Neuro-Evolution for Augmenting Topologies (NEAT). CONE-2 and NEAT are comparatively tested in a collective construction task. The goal is to ascertain the most appropriate controller evolution method for adapting teams to solve a collective construction task, with varying cooperative behavior requirements. Results indicate that CONE-2 is most effective at adapting controllers as the complexity of the task increases. In environments where multiple forms of cooperative behavior are required, CONE-2 evolves teams with a higher average task performance. CONE-2 is demonstrated as being effective at evolving behavioral heterogeneity in teams, which results in a higher team fitness, comparative to NEAT evolved teams, in environments that require cooperation.
Keywords :
adaptive control; computational complexity; multi-robot systems; neurocontrollers; CONE-2; NE methods; NEAT; behavioral heterogeneity; collective construction; collective construction task; collective neuro-evolution 2; controller adaptation; controller topology; fixed topologies; neuro-evolution for augmenting topologies; neuro-evolution methods; simulated robot teams; task complexity; Collision avoidance; Complexity theory; Mathematical model; Robot sensing systems; Topology;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Evolutionary Computation (CEC), 2012 IEEE Congress on
Conference_Location :
Brisbane, QLD
Print_ISBN :
978-1-4673-1510-4
Electronic_ISBN :
978-1-4673-1508-1
Type :
conf
DOI :
10.1109/CEC.2012.6256158
Filename :
6256158
Link To Document :
بازگشت