Everywhere AI is there the way we work, learn, shop, and now creating new opportunities for playing and watching our favorite sports.
With the help of Artificial Intelligence and Machine Learning researchers from the Institute for Big Data Analytics at Dalhousie were recently named as runners up in 2020’s largest international AI soccer simulation competition, RoboCup Japan open. RoboCup an International robotics competition uses soccer simulation to promote robotics and AI.
By 2050 they are aiming in training a team of fully autonomous humanoid robots to win a soccer game against the winner of the most recent World Cup. RoboCup uses many methods of AI and ML to train autonomous players in different positions to collaborate and play together intelligently.
These methods are bringing new ways to play and use sports especially during a time where the in-person activity is delayed. Mahtab echoes mentioned that this method of training agents makes them learn behaviors, resulting in working with most effectively and intelligently, be that the fastest or by using the least amount of energy. This can be also used in the future of video games.
Artificial Intelligence (AI) and Machine Learning (ML) controlled the outcome for the team during the RoboCup competition, but they discuss that human knowledge and experience are essential as well as they took some inspiration from the best.
Mahtab mentioned that Nader, chief architect of the RoboCup team, has developed a defensive strategy that tries to mimic the strategy of Barcelona FC. It’s not like them, but they want to make their team close to the real human players. Humans can receive more about the game from the technology and that can change the way sports are watched and played forever.
Dr. Soares commented that there will be a virtual assistant coach that can help the human coach by telling the strategy of the game isn’t working, why not replace these two players. With help of this platform, decision-making can be provided to the coach.
