Exportar Publicação

Romano, P., Nunes, L., Christensen, A. L., Duarte, M. & Oliveira, S. (2015). Genome variations: Effects on the robustness of neuroevolved control for swarm robotics systems. In Luís Paulo Reis, António Paulo Moreira, Pedro U. Lima, Luis Montano, Victor Muñoz-Martinez (Ed.), Proceedings of the ROBOT'2015: Second Iberian Robotics. Lisboa: Springer.

P. S. Romano et al.,  "Genome variations: Effects on the robustness of neuroevolved control for swarm robotics systems", in Proc. of the ROBOT'2015: 2nd Iberian Robotics, Luís Paulo Reis, António Paulo Moreira, Pedro U. Lima, Luis Montano, Victor Muñoz-Martinez, Ed., Lisboa, Springer, 2015, vol. 1

@inproceedings{romano2015_1730766061693,
	author = "Romano, P. and Nunes, L. and Christensen, A. L. and Duarte, M. and Oliveira, S.",
	title = "Genome variations: Effects on the robustness of neuroevolved control for swarm robotics systems",
	booktitle = "Proceedings of the ROBOT'2015: Second Iberian Robotics",
	year = "2015",
	editor = "Luís Paulo Reis, António Paulo Moreira, Pedro U. Lima, Luis Montano, Victor Muñoz-Martinez",
	volume = "1",
	number = "",
	series = "",
	doi = "10: 10.1007/978-3-319-27146-0_24",
	publisher = "Springer",
	address = "Lisboa",
	organization = "SPR – Sociedade Portuguesa de Robótica, SEIDROB – Sociedad Española para la Investigación y Desarrollo en Robótica and GTROB - Grupo de Robótica de CEA",
	url = "https://web.fe.up.pt/~robot2015/"
}

TY  - CPAPER
TI  - Genome variations: Effects on the robustness of neuroevolved control for swarm robotics systems
T2  - Proceedings of the ROBOT'2015: Second Iberian Robotics
VL  - 1
AU  - Romano, P.
AU  - Nunes, L.
AU  - Christensen, A. L.
AU  - Duarte, M.
AU  - Oliveira, S.
PY  - 2015
SN  - 2194-5357
DO  - 10: 10.1007/978-3-319-27146-0_24
CY  - Lisboa
UR  - https://web.fe.up.pt/~robot2015/
AB  - Manual design of self-organized behavioral control for swarms of robots is a complex task. Neuroevolution has proved a viable alternative given its capacity to automatically synthesize controllers. In this paper, we introduce the concept of Genome Variations (GV) in the neuroevolution of behavioral control for robotic swarms. In an evolutionary setup with GV, a slight mutation is applied to the evolving neural network parameters before they are copied to the robots in a swarm. The genome variation is individual to each robot, thereby generating a slightly heterogeneous swarm. GV represents a novel approach to the evolution of robust behaviors, expected to generate more stable and robust individual controllers, and benet swarm behaviors that can deal with small heterogeneities in the behavior of other members in the swarm. We conduct experiments using an aggregation task, and compare the evolved solutions to solutions evolved under ideal, noise-free conditions, and to solutions evolved with traditional sensor noise.
ER  -