Curly: An AI-based Curling Robot Successfully Competing in the Olympic Discipline of Curling
D. Won, B. Kim, H. Kim, T. Eom, K. Müller, and S. Lee. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, page 5883-5885. International Joint Conferences on Artificial Intelligence Organization, (July 2018)
DOI: 10.24963/ijcai.2018/870
Abstract
Most artificial intelligence (AI) based learning systems act in virtual or laboratory environments. Here we demonstrate an AI-based curling robot system named `Curly' that competes on a real-world curling ice sheet. Curly encompasses (1) an AI-based curling strategy and simulation engine under consideration of the high `icy' uncertainty, (2) the thrower robot enabled by autonomous driving with traction control, and (3) the skip robot that allows to recognize the curling field and stone configuration based on vision technology. The Curly performed well both: in classical game situations and when interacting with human opponents, namely, the top-ranked Korean amateur high school curling team.
%0 Conference Paper
%1 Won_2018
%A Won, Dong-Ok
%A Kim, Byung-Do
%A Kim, Ho-Jung
%A Eom, Tae-San
%A Müller, Klaus-Robert
%A Lee, Seong-Whan
%B Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
%D 2018
%E Lang, Jérôme
%I International Joint Conferences on Artificial Intelligence Organization
%K Curling
%P 5883-5885
%R 10.24963/ijcai.2018/870
%T Curly: An AI-based Curling Robot Successfully Competing in the Olympic Discipline of Curling
%U https://doi.org/10.24963%2Fijcai.2018%2F870
%X Most artificial intelligence (AI) based learning systems act in virtual or laboratory environments. Here we demonstrate an AI-based curling robot system named `Curly' that competes on a real-world curling ice sheet. Curly encompasses (1) an AI-based curling strategy and simulation engine under consideration of the high `icy' uncertainty, (2) the thrower robot enabled by autonomous driving with traction control, and (3) the skip robot that allows to recognize the curling field and stone configuration based on vision technology. The Curly performed well both: in classical game situations and when interacting with human opponents, namely, the top-ranked Korean amateur high school curling team.
@inproceedings{Won_2018,
abstract = {Most artificial intelligence (AI) based learning systems act in virtual or laboratory environments. Here we demonstrate an AI-based curling robot system named `Curly' that competes on a real-world curling ice sheet. Curly encompasses (1) an AI-based curling strategy and simulation engine under consideration of the high `icy' uncertainty, (2) the thrower robot enabled by autonomous driving with traction control, and (3) the skip robot that allows to recognize the curling field and stone configuration based on vision technology. The Curly performed well both: in classical game situations and when interacting with human opponents, namely, the top-ranked Korean amateur high school curling team. },
added-at = {2019-05-17T15:44:44.000+0200},
author = {Won, Dong-Ok and Kim, Byung-Do and Kim, Ho-Jung and Eom, Tae-San and Müller, Klaus-Robert and Lee, Seong-Whan},
biburl = {https://www.bibsonomy.org/bibtex/233bff8690d178da94f766f8af03c3a31/cckonstanz},
booktitle = {Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence},
doi = {10.24963/ijcai.2018/870},
editor = {Lang, Jérôme},
interhash = {0e5ebe91de1a5aadf7f5e6845cc1d833},
intrahash = {33bff8690d178da94f766f8af03c3a31},
keywords = {Curling},
month = jul,
pages = {5883-5885},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
timestamp = {2019-05-17T15:44:44.000+0200},
title = {Curly: An {AI}-based Curling Robot Successfully Competing in the Olympic Discipline of Curling},
url = {https://doi.org/10.24963%2Fijcai.2018%2F870},
year = 2018
}