Pushing the State-Of-The-Art
It is our intention to use RoboCup as a vehicle to promote robotics and AI research, by offering a publicly appealing, but formidable challenge. One of the effective ways to promote science and engineering research is to set a challenging long term goal. When the accomplishment of such a goal has significant social impact, it is called a grand challenge project. Building a robot that plays soccer will not by itself generate significant social and economic impact, but the accomplishment will certainly be considered a major achievement for the field. We call this kind of project a landmark project. RoboCup is a landmark project as well as a standard problem.
We proposed that the ultimate goal of the RoboCup Initiative to be stated as follows:
By the middle of the 21st century, a team of fully autonomous humanoid robot soccer players shall win a soccer game, complying with the official rules of FIFA, against the winner of the most recent World Cup.
We propose that this goal will be one of the grand challenges shared by the robotics and AI communities for the next 50 years. This goal may sound overly ambitious given the state of the art of technology today. Nevertheless, we believe it is important that such a long-range goal should be set and pursued. It took only 50 years from the Wright Brothers’ first aircraft to the Apollo mission, to send a man to the moon and safely return him to the earth. It also took only 50 years, from the invention of the digital computer to Deep Blue, which beat the human world champion in chess. Building a humanoid soccer player requires an equally long period and extensive efforts of a broad range of researchers, and the goal will not be met in the near future.
The Landmark Project
Successful landmark projects to accomplish very attractive and broadly appealing goals. The most successful example is the Apollo space program. In the case of the Apollo project, the U.S. committed to the goal of “landing a man on the moon and returning him safely to earth.” (*Urgent National Needs*, John F. Kennedy, Speech to a Joint Session of Congress*, 25 May 1961, Congressional Record — House (25 May 1961) p.8276.)
The accomplishment of the goal itself is a landmark in the history of mankind. Although the direct economic impact of having someone land on the moon is slim (To be fair, the Apollo mission was planned to gain “National Prestige” and to demonstrate technical superiority over the former Soviet Union. Even in this aspect, no direct military advantage was gained by having a few astronauts on the moon.), technologies developed to achieve this goal were so significant that they formed powerful technological and human foundations for American industries. A crucial issue for landmark projects is to set the goal high enough so that a series of technical breakthroughs is necessary to accomplish the task, and the goal needs to be widely appealing and exciting. In addition, the set of technologies necessary to accomplish the goal must be technologies which can form the foundation of the next generation of industries.
In the Apollo project, the actual goal was much more than a manned mission to the moon (PROJECT APOLLO: “THAT’S ONE SMALL STEP FOR A MAN, ONE GIANT LEAP FOR MANKIND.” The national effort that enabled Astronaut Neil Armstrong to speak those words as he stepped onto the lunar surface fulfilled a dream as old as humanity. But Project Apollo’s goals went beyond landing Americans on the Moon and returning them safely to Earth: To establish the technology to meet other national interests in space; To achieve preeminence in space for the United States; To carry out a program of scientific exploration of the Moon; To develop man’s capability to work in the lunar environment.)
In the case of RoboCup, the ultimate goal is to “develop a robot soccer team which beats the human world champion team.” (A more modest goal is “to develop a robot soccer team which plays like human players.”)
Needless to say, the accomplishment of the ultimate goal will take decades of effort. It is not feasible, with current technologies to accomplish this goal in the near future. However, this goal can easily lead to a series of well-directed subgoals. Such an approach is common in any ambitious, or overly ambitious project. In the case of the American space program, the Mercury project and the Gemini project, which manned an orbital mission, were two precursors to the Apollo mission. The first subgoal to be accomplished in RoboCup is “to build real and software robot soccer teams which play reasonably well with modified rules.” Even to accomplish this goal will undoubtedly generate technologies, which will impact a broad range of industries.
The Standard Problem
One other aspect of RoboCup is a view that RoboCup is a standard problem so that various theories, algorithms, and architectures can be evaluated. Computer chess is a typical example of such a standard problem. Various search algorithms were evaluated and developed using this domain. With the accomplishment by Deep Blue team, which beat Garry Kasparov, a human grand master, using the official rules, the computer chess challenge came close to its aim. One of the major reasons for the success of computer chess as a standard problem is that the evaluation of progress was clearly defined. The progress of the research can be evaluated as the strength of the system, which was indicated by its rating. However, as computer chess approached its goal, we needed a new challenge. The challenge needed to foster a set of technologies for the next generation of industries. We think that RoboCup will fulfill such a demand.
Difference of domain characteristics between computer chess and RoboCup.
Comparison of Chess and RoboCup
RoboCup is designed to meet the need of handling real world complexities, though in a limited world, while maintaining an affordable problem size and research cost. RoboCup offers an integrated research task covering broad areas of AI and robotics. Such areas include: real-time sensor fusion, reactive behavior, strategy acquisition, learning, real-time planning, multiagent systems, context recognition,vision, strategic decision-making, motor control, intelligent robot control, and many more.