- author = "Rikard Karlsson and Peter Nordin and Mats Nordahl",
- title = "Sound Localization for a Humanoid Robot Using Genetic Programming",
- booktitle = "Real-World Applications of Evolutionary Computing",
- year = "2000",
- editor = "Stefano Cagnoni and Riccardo Poli and George D. Smith and David Corne and Martin Oates and Emma Hart and Pier Luca Lanzi and Egbert Jan Willem and Yun Li and Ben Paechter and Terence C. Fogarty",
- volume = "1803",
- series = "LNCS",
- pages = "65--76",
- address = "Edinburgh",
- publisher_address = "Berlin",
- month = "17 " # apr,
- organisation = "EvoNet",
- publisher = "Springer-Verlag",
- keywords = "genetic algorithms, genetic programming, memory, demes",
- ISBN = "3-540-67353-9",
-
DOI = "
doi:10.1007/3-540-45561-2_7",
- abstract = "A linear GP system has been used to solve the problem of sound localization for an autonomous humanoid robot, with two microphones as ears. To determine the angle to the sound source, an evolved program was used in a loop over a stereo sample stream, where the genetic program gets the latest sample pair plus feedback from the previous iteration as input. The precision of the evolved programs was dependent on the experimental setup. For a sawtooth wave from a fixed distance the smallest error was 8 degrees. When letting the distance to the same source vary the error was 23 degrees. For a human voice at varying distances the error was up to 41 degrees",
-
notes = "GP individual run iteratively, reading current inputs
and its previous outputs (saved in two memories) as
well as generating two real valued outputs. Training
data presented in as time series one sample (8 or
16bits at 16kHz). 40 samples.
Pop 40000 split into ten demes. Homologous crossover. Ears important.
EvoWorkshops 2000: EvoIASP, EvoSCONDI, EvoTel, EvoSTIM, EvoRob, and EvoFlight, Edinburgh, Scotland, UK, April 17, 2000 Proceedings
http://evonet.lri.fr/evoweb/resources/books_journals/record.php?id=61",
