e-Sport Simulation Feasability Study The German company aitainment GmbH is developing new generation e-sports games. The company was co-founded by Dr. Visser, a Visiting Associate Professor at the Department of Computer Science of the University of Miami. The company’s first products are based on a newly developed and modern AI technology, embodied in virtual players, and on a newly developed 3D graphics engine. The first target group is all users who are interested in soccer. Further developments include other sports (e.g. ice hockey, football, baseball) and other devices (e.g. mobile phones). The goals of this feasibility study are twofold. Firstly, a thorough marketing analysis will give an overview about the market. We show the competition in all relevant sports such as football, baseball, ice hockey, and basketball with an emphasis on football and baseball. The market analysis is based on a number of criteria that includes technology, genre, gameplay, social networking, art style, player data, expandability, commercialization, and popularity (see section 2.1 for details). Secondly, requirements and goals for a new game are presented and discussed. Results of this study show that there our technology can be used for some of the mentioned sports (e.g. baseball) but need further development, especially for the task of collision detection if used for other sports (e.g. football, basketball).
Motion Capture Animation Motion capture technology is a good example of how digital techniques can be applied to video games. It is one way of allowing convincing visualizations of imaginary or complex motions. Motion capture can be done using several techniques:
The University of Miami has a motion capture lab that is based on Passive markers with retroreflective material (Vicon system). There are 10 4-megapixel cameras (120 Hz) and 2 video cameras. Four force plates to measure forces on ground are also available. There are also facilities to capture facial expressions and electromagnetic devices to capture voltage in max 16 muscles groups for biomedical studies. The AI & Games group made experiments with complex sports motions using soccer as an example. Here are some of the results:
RoboCup RoboCupTM is an international research and education initiative. Its goal is to foster artificial intelligence and robotics research by providing a standard problem where a wide range of technologies can be examined and integrated. The concept of soccer-playing robots was first introduced in 1993. Following a two-year feasibility study, in August 1995, an announcement was made on the introduction of the first international conferences and football games. In July 1997, the first official conference and games were held in Nagoya, Japan. Followed by Paris, Stockholm, Melbourne and Seattle where the annual events attracted many participants and spectators. The 6th RoboCup 2002 was held in Fukuoka, Japan in cooperation with Busan, Korea, while the 7th edition in 2003 took place in Padua, Italy. In 2004 in Lisbon, Portugal. 2005 in Osaka, Japan, 2006 in Bremen, Germany, 2007 in Atlanta, USA, and and now in Suzhou, China. The events were covered by national and international media all over the world. RoboCup consists of four different areas in RoboCup: RoboCupSoccer, RoboCupRescue, RoboCup@Home, and RoboCupJunior. The University of Miami, students lead by Professor Ubbo Visser are working RoboCupSoccer team that will start with a 3D Soccer Simulation team. The team hopes to qualify and compete in the RoboCup World Soccer tournament in 2010 in Singapore. The team's research focusses the investigation of situation recognition and opponent intentions for action selection in adversarial multiagent environments. Another focus includes the interpretation and prediction of simple and complex motion scenes using qualitative spatio-temporal descriptions and additional background knowledge. This approach is domain independent and therefore can be used in various applications. Further studies have led to a general idea of this approach. The hypothesis is to use a qualitative representation of the agent's world on a higher abstraction level. This means, we can use deliberation methods in order to define strategies and tactics and provide well-defined interfaces for the actual plans and actions on a lower level. Useful links: Official RoboCup Site: http://www.robocup.org |
|||
 |
AI & Games Group |
|
|
|
|
© 2009-2011 AI & Games Group of University of Miami |
|
|
