Skip to content

docs(action) clarify AgiBotWorld URDF scope - #338

Open
sylvesterkaczmarek wants to merge 1 commit into
NVIDIA:mainfrom
sylvesterkaczmarek:docs/clarify-agibot-urdf-305
Open

docs(action) clarify AgiBotWorld URDF scope#338
sylvesterkaczmarek wants to merge 1 commit into
NVIDIA:mainfrom
sylvesterkaczmarek:docs/clarify-agibot-urdf-305

Conversation

@sylvesterkaczmarek

Copy link
Copy Markdown

Summary

  • clarify that the public AgiBotWorld FK path uses G1_omnipicker_calibrated.urdf as a kinematics reference
  • document that the URDF's referenced visual mesh package is not bundled in robot_assets
  • explain that the FK loader strips visual and collision elements before constructing its MuJoCo kinematics model
  • clarify that the committed file is not a complete renderable description for every AgiBotWorld gripper variant

Why

Issue #305 asks why the AgiBotWorld Beta data appears to use a CTEK gripper while the available URDF is an omnipicker description, and asks for the complete mesh-backed URDF.

The current public Cosmos Framework hard-codes G1_omnipicker_calibrated.urdf for the AgiBotWorld FK path. The URDF contains package://genie_robot_description/meshes/... references, but the corresponding mesh package is not included in the public robot_assets directory. This does not block the current action FK path because the loader explicitly removes <visual> and <collision> elements before loading the model into MuJoCo.

This documentation change makes the scope of the published robot description explicit and avoids implying that it is a complete renderable CTEK/omnipicker asset package.

Validation

Documentation-only change. Cross-checked against agibot_spec.py, agibot_fk.py, the committed G1_omnipicker_calibrated.urdf, and the current robot_assets directory in NVIDIA/cosmos-framework.

Addresses #305

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant