TensorFlow for FIRST SKYSTONE

The game release has come! Now it’s time to build and program your robot. For this year’s game, one scoring opportunity is to recognize and move skystones in autonomous mode. For this season, you have the option to use specialized machine learning software to simplify the task of identifying and tracking the game elements during autonomous mode.

TensorFlow, Google’s “machine learning technology,” has been trained to recognize the game elements from this season’s challenge. You can use this technology to program your robot to look for and navigate to game elements, such as a skystone.

Bruce Schafer, from the Oregon Robotics Tournament and Outreach Program, has created a video tutorial that demonstrates how to use TensorFlow to find and navigate autonomously to seek and find a skystone for this season’s challenge:

The sample Blocks Op Mode that accompanies Bruce’s tutorial video can be found here:

File to upload: www.tinyurl/SeekSkystoneBLK

Printable code: www.tinyurl/SeekSkystonePrint

Thank you to Bruce Schafer for his work on the TensorFlow tutorial! FIRST Tech Challenge appreciates his contributions to improving the experience for our teams!

Advertisements

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 )

Google photo

You are commenting using your Google 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 )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.