Visualizing Open X-Embodiment datasets in Foxglove

July 9, 2025 ยท View on GitHub

These are the tutorial files that show how you can visualize Open-X Embodiment dataset in Foxglove.

To execute the script, you will need to install the following Python dependencies:

tensorflow
gcsfs
foxglove-sdk
tensorflow_datasets

We include a layout foxglove_tutorials/open_x_embodiment/layouts/berkeley_autloab_ur5_layout.json that you can use to view all the data that we included in the tutorial.

Running the script

  1. Run the Python script: python3 visualize_berkeley_autolab_ur5.py
  2. In Foxglove, open a remote connection to ws://localhost:8765
  3. Arrange panels to visualize the data, or use the layout included in this tutorial: open_x_embodiment/layouts/berkeley_autloab_ur5_layout.json