Carnegie Mellon Wins Fifth International RoboCup

The CMDragons, a robot soccer team developed by computer scientists from Carnegie Mellon University (CMU), have won the 2015 Robot World Cup Initiative (RoboCup), which was held on July 22 in Hefei, China.

RoboCup is an annual international robotics competition launched in 1997 to promote robotics and artificial intelligence research. This is the fifth year in a row that the CMDragons have won the world championship in the Small Size League (SSL), one of five leagues in the soccer competition. Other leagues are Humanoid, Middle Size, Simulation and Standard Platform.

A robot soccer game in the Small Size League involves two teams of six robots, each less than six inches high, playing with an orange golf ball on a modified indoor soccer "field." Overhead cameras can identify each robot by a color-coded pattern on its top and determine its position and orientation. The computer scientists use off-field computers to communicate commands and strategies. The CMDragons won the final round of the competition with a score of 5-to-0 over a team from Qazvin Islamic Azad University in Iran.

Manuela Veloso, a computer science professor at CMU, advises the team and helped to launch the RoboCup initiative in 1997. This year, the team was led by Joydeep Biswas, a computer science post-doctoral fellow and recent graduate of the Robotics Institute's doctoral program, and Juan Pablo Mendoza, a doctoral student at the Robotics Institute.

The team's original robots were created by former CMU researcher Mike Licitra. This year Biswas and Richard Wang, a computer science doctoral student at CMU, enhanced the hardware of the team's original robots. Biswas and Philip Cooksey, a doctoral student at the Robotics Institute, developed the individual motion execution and ball-kicking and dribbling capabilities of the robots. Mendoza, Wang and Steven Klee, a computer science master's degree student at CMU, worked on robot collaboration.

According to a news release from the university, the CMU team "developed the best algorithm Veloso has seen for 'game on' play, which requires a higher level of adaptability than set plays teams use following ball stoppage."

Since its inception, the RoboCup has grown to include other events beyond RoboCupSoccer. The RoboCupRescue competition tests the ability of robots to assist emergency responders and perform hazardous tasks. RoboCup@Home involves robots that help people with their daily lives in and out of the home. And RoboCupJunior is a robotic competition for elementary, high school and undergraduate students.

About the Author

Leila Meyer is a technology writer based in British Columbia. She can be reached at [email protected].

Featured

  • humanoid robot with circuit board background

    Meta Expands into Physical AI with Acquisition of Robotics AI Startup

    Meta Platforms has acquired Assured Robot Intelligence (ARI), a robotics artificial intelligence startup focused on humanoid systems, as the company expands its AI work beyond software and into models that could help robots operate in physical environments.

  • Neon blue security locks with a single red highlight

    AI Shifts Cybersecurity Focus from Finding Flaws to Fixing Them

    For decades, one of cybersecurity's most difficult challenges has been finding vulnerabilities before attackers do. A growing number of security professionals now say artificial intelligence is changing that equation, shifting the focus from discovering flaws to fixing them quickly enough to prevent exploitation.

  • abstract smartphone translucent screen displaying AI interface

    Apple Introduces Redesigned Siri AI

    At its recent Worldwide Developers Conference, Apple introduced Siri AI, a redesigned version of its voice assistant that Apple describes in its own announcement as "a profoundly more capable and personal assistant." The update is intended to make Siri more conversational, more context-aware, and more useful across iPhone, iPad, Mac, Apple Watch, and Vision Pro.

  • Blue digital wireframe classical building structure

    Before AI, Fix Your Data

    Institutions don't have to solve every data problem before they can begin using AI responsibly. But they do need to treat information as a strategic asset — not a byproduct of operations — and start building toward AI-ready data now.