CYRUS, the AI-based team built by Dalhousie computer science PhD student Mahtab Sarvmaili and senior research assistant Nader Zare, won the Simulation 2D league of RoboCup 2021 on June 27.
This international robotics competition uses soccer simulation to promote robotics and AI research with the research findings used to advance many areas. By 2050, 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.
Using AI and machine learning to mimic the behaviour of the likes championship soccer players, the team from Dalhousie’s Institute for Big Data Analytics won all of the games played against their opponents leading to the finals of the competion. In addition to CYRUS, the 16 participating teams in the league include representatives from universities in China, Iran, Germany, Brazil, Japan and Romania.
Stan Matwin, Canada Research Chair and director of the Institute for Big Data Analytics notes, “This is a new way of using AI where we use a whole range of AI methods to create a simulation of perception so that the agents or ‘players’ work autonomously but also learn how to collaborate.”