Robots Improve Their Soccer Skills Using Physics Principles

Researchers from Carnegie Mellon University are trying to teach machines to improve their soccer playing skills.

Presented at the RoboCup 2010 world championship, that will take place in Singapore and will be opened for the public in the period between June 19 and 25, the robot soccer players make use of a new algorithm that makes it possible for the machines to predict the behavior of the soccer ball.

It is worth mentioning that the new algorithm allows the robots to analyze and estimate the future behavior of the ball based on physics principles.

The RoboCup world championship features 5 robot soccer leagues, along with competitions for search-and-rescue machines, assistive robots and students aged up to 19.

“Physics-based planning gives us an advantage when a robot is dribbling the ball and needs to make a tight turn, or any other instance that requires an awareness of the dynamics of the ball,” explained Stefan Zickler, the author of the new algorithm.

According to Manuela Veloso, professor of computer science and leader of Carnegie Mellon’s two robot soccer teams, the biggest challenge that AI faces today lies in finding a way to teach robots to coordinate with each other and do so in surroundings with high uncertainty.

Advertisements
  1. Leave a comment

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: