A team of researchers from the Institute for Big Data Analytics at Dalhousie University has secured gold at the largest artificial intelligence soccer competition, highlighting Canadian AI innovation in team robotics technology
HALIFAX, NS, July 28, 2021 /CNW/ - The Dalhousie University robotics team, CYRUS, announces its victory against reigning world champions, Japan-based HELIOS2021, becoming the first Canadian team to secure first place in the international RoboCup competition. Led by research assistant Nader Zare and PhD student Mahtab Sarvmaili, both in the Faculty of Computer Science, the team utilized a variety of AI and machine learning models to train autonomous 'players' in different positions. Through intelligent programming, the robots collaborated and were able to play together, often mimicking the behaviour of the world's best soccer teams and players.
RoboCup, a worldwide competition that shifted to a fully remote model for 2021, uses soccer simulation to promote robotics and AI research. Capitalizing on the rapid acceleration of AI research and robotics innovation, the competition aims to train a team of fully autonomous humanoid robots to win a soccer game against the winner of the most recent World Cup by 2050.
"This is an incredible achievement for Team CYRUS and for Dalhousie," says Dr. Stan Matwin, Canada Research Chair and director of the Institute for Big Data Analytics. "It demonstrates that Nova Scotia is really starting to lead the way in areas of AI and machine learning research."
While these methods are presenting new ways to play and consume sports, particularly at a time when in-person activity has largely been suspended, the team is using its research to help humans improve their soccer techniques through a collaboration with the Halifax Wanderers and Dalhousie University's Varsity soccer teams. In particular, this emerging project will help the teams better understand their players and team dynamics through data analysis, using some of the AI methods developed for RoboCup.
Outside of soccer, the research findings of CYRUS are critical and used to advance the solutions for many real-world issues. Highlighting the relationships between teams, effective tactical plays and how to mobilize teams for a common goal, CYRUS' findings can be directly translated to supporting other team sports, as well as the police, military and emergency response teams.
"The concentration and innovation of Canadian AI and robotics research has been steadily on the rise, but CYRUS' ability to secure the championship is a clear indication of our national and provincial excellence within this field of research," shares Mahtab Sarvmaili, PhD student at Dalhousie University's Faculty of Computer Science. "The team looks forward to taking our success to the next level and not only assisting our local sports teams, but also applying our technology on a national scale in support of our emergency responders and tactical teams."
For more information, please visit www.dal.ca. The final round of RoboCup 2021 can be viewed here.
ABOUT CYRUS
CYRUS is an AI-based team from the Dalhousie University's Institute for Big Data Analytics, built by Faculty of Computer Science PhD student Mahtab Sarvmaili and senior research assistant Nader Zare. Founded in 2012, the team has been participating in robotics competitions around the world over the past nine years, using a variety of AI and machine learning models that can be translated into a wide range of applications such as computer games; autonomous robots; training sports teams, the police or military, and natural disaster search and rescue operations.
SOURCE CYRUS

For media inquiries, please contact: Aleesha McMullin, Durrell Communications, 519-803-4797, [email protected]
Share this article