Skip top navigation and go to page content
National Science Foundation
Computer & Information Science
next page Computing Home
next page More Research Overviews
CMPack'02, Carnegie Mellon robot soccer team
Members of the Carnegie Mellon robot soccer team, CMPack'02, which won first place at RoboCup 2002 in Fukuoka, Japan. In the final game, CMPack'02 played the rUNSWift team from the University of New South Wales, Australia. The game ended in a 3-3 tie. CMPack'02 won 5-4 in a penalty shoot out.
Credit: CMPack'02 research team: Manuela Veloso, Scott Lenser, Douglas Vail, Maayan Roth, Ashley Stroupe, Sonia Chernova. Photo by Debra Tobin.

A Team of your own
Information overload is a fact of life these days, but in an ideal world, it wouldn't be. You'd get exactly the information you need, when you need it and use it to take action. To get that done, you'd need the help of your own intelligent team.

Building such a team ranks as one example of a grand challenge for information systems. Some members of your team, called "agents," will exist solely as software in the digital realm. Other team members will be robots that sense and interact with the physical world.

A person with physical or medical challenges, for example, might have a team to help him to live safely on his own. Software agents will monitor vital signs and communicate with health care providers, while robots help around the house or provide mental stimulation.

Emergency response personnel would benefit from a team trained in search-and-rescue operations. Robots would enter collapsed buildings and bring food and water to trapped victims. Software agents would track down blueprints and maps or communicate relevant data from cooperating agencies.

Research is needed to give the robots and agents the appropriate intelligence. Team members should be independent and capable of learning, but they should also know when ask guidance of and obey instructions from their human leader -- and do so in human terms. A second research challenge is teamwork. Both sports coaches and information technology teams face similar hurdles: ensuring the players communicate, adapting to the team's strengths and limitations, coordinating the different skills and practicing to hone and learn skills.

Many NSF programs -- in robotics, sensors and human-computer interaction, to name a few -- play a role in meeting this grand challenge. The Science and Engineering Information Integration and Informatics program, for example, focuses on a critical skill for software agents: the collection and analysis of timely, accurate and reliable information from wide-ranging sources. 

Not to be overlooked, of course, is the issue of trust. You must be able to count on your team to do what you expect, to safeguard your private information, to support teammates in unexpected situations and to make your life better, not worse.

A Teacher for Every Learner [Next]

The Computing Research Association outlined five illustrative Grand Research Challenges in a report resulting from a three-day workshop supported by the National Science Foundation. The grand challenges relate to building the information systems of the future and provide long-term goals for the activities of the research community.