Tutorial: Calculate the Position of Detected Objects with ROS 1 Transforms

ROS transforms hep you position your robot’s components in relation to each other, but they can also be used to describe your robots’ relation to the world they navigate.

Check out the latest tutorial on the Foxglove blog to learn how to calculate the position of detected objects, using the ROS tf2 library:

For a reference to all the code covered in the tutorial, check out the foxglove/tutorials GitHub repo. And as always, feel free to comment below or reach out to us in our Slack community to request a topic for the next tutorial.


Yeah!! Absolutely. Representing objects detections as frames (fixed frames as odom or map) is a good strategy. When you do this, you can calculate its position with respect any frame for approach, pick, look again,…