Exportar Publicação

A publicação pode ser exportada nos seguintes formatos: referência da APA (American Psychological Association), referência do IEEE (Institute of Electrical and Electronics Engineers), BibTeX e RIS.

Exportar Referência (APA)
Gomes, J., Urbano, P. & Christensen, A. L. (2013). Evolution of swarm robotics systems with novelty search. Swarm Intelligence. 7 (2-3), 115-144
Exportar Referência (IEEE)
J. Gomes et al.,  "Evolution of swarm robotics systems with novelty search", in Swarm Intelligence, vol. 7, no. 2-3, pp. 115-144, 2013
Exportar BibTeX
@article{gomes2013_1720128051000,
	author = "Gomes, J. and Urbano, P. and Christensen, A. L.",
	title = "Evolution of swarm robotics systems with novelty search",
	journal = "Swarm Intelligence",
	year = "2013",
	volume = "7",
	number = "2-3",
	doi = "10.1007/s11721-013-0081-z",
	pages = "115-144",
	url = "https://link.springer.com/article/10.1007%2Fs11721-013-0081-z"
}
Exportar RIS
TY  - JOUR
TI  - Evolution of swarm robotics systems with novelty search
T2  - Swarm Intelligence
VL  - 7
IS  - 2-3
AU  - Gomes, J.
AU  - Urbano, P.
AU  - Christensen, A. L.
PY  - 2013
SP  - 115-144
SN  - 1935-3812
DO  - 10.1007/s11721-013-0081-z
UR  - https://link.springer.com/article/10.1007%2Fs11721-013-0081-z
AB  - Novelty search is a recent artificial evolution technique that challenges traditional evolutionary approaches. In novelty search, solutions are rewarded based on their novelty, rather than their quality with respect to a predefined objective. The lack of a predefined objective precludes premature convergence caused by a deceptive fitness function. In this paper, we apply novelty search combined with NEAT to the evolution of neural controllers for homogeneous swarms of robots. Our empirical study is conducted in simulation, and we use a common swarm robotics task—aggregation, and a more challenging task—sharing of an energy recharging station. Our results show that novelty search is unaffected by deception, is notably effective in bootstrapping evolution, can find solutions with lower complexity than fitness-based evolution, and can find a broad diversity of solutions for the same task. Even in non-deceptive setups, novelty search achieves solution qualities similar to those obtained in traditional fitness-based evolution. Our study also encompasses variants of novelty search that work in concert with fitness-based evolution to combine the exploratory character of novelty search with the exploitatory character of objective-based evolution. We show that these variants can further improve the performance of novelty search. Overall, our study shows that novelty search is a promising alternative for the evolution of controllers for robotic swarms.
ER  -