Export Publication

Gomes, J., Mariano, P. & Christensen, A. L. (2015). Cooperative coevolution of morphologically heterogeneous robots. In ECAL 2015: the 13th European Conference on Artificial Life. (pp. 312-319). York: MIT Press.

J. F. Gomes et al.,  "Cooperative coevolution of morphologically heterogeneous robots", in ECAL 2015: the 13th European Conf. on Artificial Life, York, MIT Press, 2015, pp. 312-319

@inproceedings{gomes2015_1716090067138,
	author = "Gomes, J. and Mariano, P. and Christensen, A. L.",
	title = "Cooperative coevolution of morphologically heterogeneous robots",
	booktitle = "ECAL 2015: the 13th European Conference on Artificial Life",
	year = "2015",
	editor = "",
	volume = "",
	number = "",
	series = "",
	doi = "10.1162/978-0-262-33027-5-ch059",
	pages = "312-319",
	publisher = "MIT Press",
	address = "York",
	organization = "The International Society for Artificial Life",
	url = "https://direct.mit.edu/isal/ecal2015/volume/27"
}

TY  - CPAPER
TI  - Cooperative coevolution of morphologically heterogeneous robots
T2  - ECAL 2015: the 13th European Conference on Artificial Life
AU  - Gomes, J.
AU  - Mariano, P.
AU  - Christensen, A. L.
PY  - 2015
SP  - 312-319
SN  - 1064-5462
DO  - 10.1162/978-0-262-33027-5-ch059
CY  - York
UR  - https://direct.mit.edu/isal/ecal2015/volume/27
AB  - Morphologically heterogeneous multirobot teams have
shown significant potential in many applications. While cooperative coevolutionary algorithms can be used for synthesising controllers for heterogeneous multirobot systems, they
have been almost exclusively applied to morphologically homogeneous systems. In this paper, we investigate if and
how cooperative coevolutionary algorithms can be used to
evolve behavioural control for a morphologically heterogeneous multirobot system. Our experiments rely on a simulated task, where a ground robot with a simple sensor-actuator
configuration must cooperate tightly with a more complex
aerial robot to find and collect items in the environment. We
first show how differences in the number and complexity of
skills each robot has to learn can impair the effectiveness of
cooperative coevolution. We then show how coevolution’s
effectiveness can be improved using incremental evolution or
novelty-driven coevolution. Despite its limitations, we show
that coevolution is a viable approach for synthesising control
for morphologically heterogeneous systems.
ER  -