How to cite this WIREs title:
WIREs Cogn Sci

Robot soccer

Advanced Review

Claude Sammut

Published Online: Jul 27 2010

DOI: 10.1002/wcs.86

How to cite this article
Download citation
Contact the editor about this article
Authors: submit updates and notes
Comment on this article
Share

Full article on Wiley Online Library: HTML PDF

Can't access this content? Tell your librarian.

Robot soccer is a test bed for a variety of robotic and Artificial Intelligence (AI) methods. Its relevance to Cognitive Science is that it confronts the designer with a task that requires the integration of almost all aspects of AI to create an agent that is capable of working in a complex, dynamic environment inhabited by other agents, some of which are cooperative and others competitive. We describe the main elements that make up a robot soccer player and how these players associate to create effective teams. We pay special attention to the architecture of the players. WIREs Cogn Sci 2010 1 824–833

Figure 1.

(a) Sony's Aibo ERS‐7 and (b) the Aldebaran Nao.

[ Normal View 39K | Magnified View 56K ]

Figure 2.

The soccer field (from the Standard Platform League Nao Rule Book10).

[ Normal View 21K | Magnified View 27K ]

Figure 3.

A RoboCup rescue arena.

[ Normal View 34K | Magnified View 51K ]

Figure 4.

Architecture of a soccer robot.

[ Normal View 7K | Magnified View 19K ]

Figure 5.

3D YUV Color space. The data represent pixels that have been manually labeled with the correct color. These can be used as training data for learning color regions.

[ Normal View 35K | Magnified View 59K ]

Figure 6.

Line detection is done by scanning bottom to top with increasing resolution.

[ Normal View 31K | Magnified View 44K ]

Figure 7.

The world model of two robots on the ‘blue’ team. Blue ellipses represent blue robots; red ellipses represent red robots; orange represents the robot's estimate of where the ball is; and pink is the other teammate's estimate of where the ball is. The gray arc is the robot's heading.

[ Normal View 40K | Magnified View 61K ]

Figure 8.

The trajectory of ‘paws’ can be described by a simple figure whose parameters are easy to tune for different walks.

[ Normal View 21K | Magnified View 30K ]

Figure 9.

Behaviors implemented as a decision tree.

[ Normal View 28K | Magnified View 39K ]

References

1 DARPA Grand Challenge. Available at: . (Accessed July 7, 2010).
2 International Planning Competition. Available at: . (Accessed July 7, 2010).
3 Reinforcement Learning Competition. Available at: . (Accessed July 7, 2010).
4 RoboCup. Available at: . (Accessed July 7, 2010).
5 Mackworth, AK. %22On seeing robots%22. In: Basu, A, Li, X, eds. Computer Vision: Systems, Theory, and Applications. Singapore: World Scientific Press; 1993, 1–13.
6 Kitano, H, Tambe, M, Stone, P, Veloso, M, et al., eds. %22The RoboCup Synthetic Agent Challenge 97%22. IJCAI97. San Francisco, CA: Morgan Kaufmann; 1997.
7 Asada, M, Kuniyoshi, Y, Drogoul, A, Asama, H, Mataric, M, et al. The RoboCup physical agent challenge: phase‐I. Appl Artif Intell 1998, 2: 251–263.
8 Fujita, M, Kitano, H. Development of an autonomous quadruped robot for robot entertainment. Auton Robots 1998, 5: 7–18.
9 Gouaillier, D, Hugel, V, Blazevic, P, Kilner, C, Monceaux, J, et al. The NAO humanoid: a combination of performance and affordability. CoRR2008;abs/0807.3223.
10 Standard Platform League Nao Rule Book. Available at: . (Accessed July 7, 2010).
11 Dissanayake, G, Newman, P, Clark, S, Durrant‐Whyte, H, Csorba, M. A solution to the simultaneous localization and map building (SLAM) problem. IEEE Trans Rob Auton 2001, 17: 229–241.
12 Sammut, C, Hengst, B. %22The evolution of a robot soccer team%22. In: Jarvis, RA, Zelinksky, A, eds. Robotics Research: The Tenth International Conference. Berlin: Springer; 2003, 517–529.
13 Simon, H. %22A behavioral model of rational choice%22. Models of Man, Social and Rational: Mathematical Essays on Rational Human Behavior in a Social Setting. New York: John Wiley %26 Sons; 1957.
14 Chen, S, Siu, L, Vogelgesang, T, Yik, TF, Hengst, B, et al. %22The UNSW RoboCup 2001 Sony Legged Robot League Team%22. In: Birk, A, Coradeschi, S, Tadokoro, S, eds. RoboCup 2001: Robot Soccer World Cup V. Berlin: Springer; 2002, 39–48.
15 Cameron, D, Barnes, N. %22Knowledge‐based autonomous dynamic colour calibration%22. In: Polani, D, Bonarini, A, Browning, B, Yoshida, K, eds. Proceedings of the RoboCup Symposium. Padua; 2004, 226–237.
16 Sridharan, M, Stone, P. Color learning on a mobile robot: towards full autonomy under changing illumination. The International Joint Conference on Artificial Intelligence, India; 2007, 2212–2217.
17 Henderson, N, King, R, Chalup, S. %22An automated color calibration system using multivariate Gaussian mixtures to segment HSI color space%22. In: Kim, J, Mahony, R, eds. Australasian Conference on Robotics and Automation; Canberra: ARAA; 2008.
18 Rofer, T, Jungel, M. %22Fast and robust edge‐based localization in the Sony four‐legged robot league%22. In: Polani, D, Bonarini, A, Browning, B, Yoshida, K, eds. RoboCup 2003: Robot Soccer World Cup VII. Berlin: Springer; 2004, 262–273.
19 Lettvin, JY, Maturana, HR, Mcculloch, WS, Pitts, WH. What the frog`s eye tells the frog`s brain. Proc IRE 1959, 47: 1940–1951.
20 Thrun, S, Burgard, W, Fox, D. Probabilistic Robotics. Cambridge, MA: MIT Press; 2005.
21 Hengst, B, Pham, SB, Ibottson, D, Sammut, C. Omnidirectional Locomotion for Quadruped Robots. RoboCup 2001: Robot Soccer World Cup V. Berlin: Springer; 2002, 368–373.
22 Kim, MS, Uther, W, eds. %22Automatic gait optimisation for quadruped robots%22. Australasian Conference on Robotics and Automation; 2003.
23 Hornby, GS, Fujita, M, Takamura, S, Yamamoto, T, Hanagata, O, eds. %22Evolution of gaits with the Sony quadruped robot%22. Proceedings of the Genetic and Evolutionary Computation Conference. San Francisco, CA: Morgan Kaufmann; 1999.
24 Kohl, N, Stone, P, eds. %22Policy gradient reinforcement learning for fast quadrupedal locomotion%22. Proceedings of the IEEE International Conference on Robotics and Automation; 2004, 2619–2624.
25 Gat, E, ed. %22Integrating planning and reaction in a heterogeneous asynchronous architecture for controlling mobile robots%22. Proceedings of the Tenth National Conference on Artificial Intelligence (AAAI); San Jose, CA: AAAI Press; 1992.
26 Gat, E. %22Three‐layer architectures%22. In: Kortenkamp, D, Bonnasso, RP, Murphy, R, eds. Artificial Intelligence and Mobile Robots. Menlo Park, CA: AAAI Press; 1998.
27 Stone, P, Sutton, RS. Scaling reinforcement learning toward RoboCup soccer. The Eighteenth International Conference on Machine Learning, Williamstown, MA, 2001, 537–544.
28 Gabel, T, Lange, S, Lauer, M, Riedmiller, M, eds. %22Bridging the gap: learning in the robocup simulation and midsize league%22. Proceedings of the 7th Portuguese Conference on Automatic Control; Lisbon, APCA: 2006.
29 Levesque, HJ, Reiter, R, Lin, F, Scherl, RB. GOLOG: a logic programming language for dynamic domains. J Logic Program 1997, 31: 59–84.
30 Ferrein, A, Lakemeyer, G. Logic‐based robot control in highly dynamic domains. Rob Auton Syst 2008, 56: 980–991.
31 Levy, D. Robots Unlimited: Life in a Virtual Age. Natick, MA: A K Peters Ltd; 2005.
32 Turing, AM. Computing machinery and intelligence. Mind 1950, 59: 433–460.

Resources

All of the RoboCup competitions are accompanied by a symposium in which the scientific contributions of the teams are presented. All of the proceedings from 1997 to 2008 have been published in Springer’s Lectures Notes in Artificial Intelligence series.

MEDIA COVERAGE

One of Alpha Galileo's most popular releases of September 2010.

See associated press release on the Chinese portal ScienceNet.

blog comments powered by Disqus

Access to this WIREs title is by subscription only.

Recommend to Your
Librarian Now!

The latest WIREs articles in your inbox

In the Spotlight

Konrad Körding

Konrad Körding is Assistant Professor of Physiology and Physical Medicine and Rehabilitation at the Rehabilitation Institute of Chicago, part of Northwestern University. Before joining Northwestern in 2006, Professor Körding worked in three different research groups, most recently in 2004-2005 at MIT, studying machine learning and hierarchical Bayesian models.

Professor Körding is a member of the Swiss Society for Neuroscience, the German Society for Neuroscience, the Society for Neuroscience (USA) and the Electronic Frontier Foundation.

Professor Körding’s current research with the Bayesian Behavior group aims to improve rehabilitation procedures through a greater understanding of motor learning. In order to do this the team studies how people move, and how these movements are affected by uncertainty.

Learn More

Article Title	Robot soccer
* Name
* E-mail
* Note

Robot soccer

Browse by Topic

Access to this WIREs title is by subscription only.

The latest WIREs articles in your inbox

In the Spotlight

Twitter: WIREsCogScience Follow us on Twitter