Update COMPASS training doc

docs/source/policy_deployment/03_compass_with_NuRec/compass_navigation_policy_with_NuRec.rst

@@ -1,27 +1,63 @@
-Training & Deploying COMPASS Navigation Policy with Real2Sim NuRec
-====================================================================
+Training and Deploying COMPASS Policies with NuRec Assets
+=========================================================
 
-COMPASS (Cross-embodiment Mobility Policy via Residual RL and Skill Synthesis) trains and
-deploys cross-embodiment navigation policies on NuRec Real2Sim assets — photoreal
-Gaussian-splat reconstructions of real spaces — in Isaac Lab.
+`COMPASS <https://arxiv.org/abs/2502.16372>`_ (Cross-embodiment Mobility Policy via Residual RL and
+Skill Synthesis) trains navigation policies that can transfer across robot embodiments. Isaac Lab supports
+COMPASS training with NuRec scene assets, so policies can be developed in reconstructed real-world
+environments instead of relying only on hand-authored simulation scenes.
 
-This tutorial now lives in the **COMPASS handbook**, next to the code it documents, where it
-stays in sync with the NuRec support branch.
+This page gives a short overview of the supported NuRec assets and example COMPASS training clips. For
+installation, asset registration, training, evaluation, export, and ROS 2 deployment instructions, see the
+`COMPASS handbook <https://github.com/NVlabs/COMPASS/blob/real2sim/isaaclab_3.0/docs/handbook/workflows/nurec_real2sim.md>`_.
 
-Where to find it
-----------------
+NuRec Assets for COMPASS
+------------------------
+
+NuRec assets matter for COMPASS because they allow navigation policies to train in simulation on realistic
+geometry, visual appearance, and obstacle layouts. This, in turn, should reduce the sim-to-real gap between
+training scenes and real operating environments and improve zero-shot transfer. They also make it possible
+to evaluate policies in reconstructed simulation scenes that better reflect target deployment spaces.
+
+Some sample assets compatible with COMPASS training are available in the
+`PhysicalAI-Robotics-NuRec dataset on Hugging Face <https://huggingface.co/datasets/nvidia/PhysicalAI-Robotics-NuRec/tree/v0.2>`_.
+
+Real2Sim Assets
+~~~~~~~~~~~~~~~
+
+`NVIDIA Neural Reconstruction (NuRec) <https://docs.nvidia.com/nurec/index.html>`_ converts real-world
+sensor data into digital simulation-ready assets for training and testing Physical AI agents. The Real2Sim
+workflow converts stereo RGB captures into Isaac Sim-ready assets with aligned geometry, collision meshes,
+and simulation-ready scene augmentation. The PhysicalAI-Robotics-NuRec dataset includes several robotics
+scenes produced with this workflow; two examples are:
+
+- `Galileo <https://huggingface.co/datasets/nvidia/PhysicalAI-Robotics-NuRec/tree/v0.2/nova_carter-galileo>`_ —
+  Embodiment: `Nova Carter <https://robotics.segway.com/nova-carter/>`_,
+  Sensor Rig: 4 x `Stereo Camera <https://leopardimaging.com/wp-content/uploads/2024/07/LI-AR0234CS-STEREO-GMSL2-30_Datasheet_V1.8.pdf>`_
 
-- **Repository:** `COMPASS on GitHub <https://github.com/NVlabs/COMPASS>`_
-- **Branch:** ``samc/support_nurec_assets_isaaclab_3.0`` (NuRec Real2Sim support)
-- **Guide:** `docs/handbook/workflows/nurec_real2sim.md <https://github.com/NVlabs/COMPASS/blob/samc/support_nurec_assets_isaaclab_3.0/docs/handbook/workflows/nurec_real2sim.md>`_ in the COMPASS repository.
+- `Living Room <https://huggingface.co/datasets/nvidia/PhysicalAI-Robotics-NuRec/tree/v0.2/hand_hold-endeavor-livingroom>`_ —
+  Embodiment: Hand-Held,
+  Sensor Rig: 1 x `Stereo Camera <https://leopardimaging.com/wp-content/uploads/2024/07/LI-AR0234CS-STEREO-GMSL2-30_Datasheet_V1.8.pdf>`_
+
+XGRIDS Assets
+~~~~~~~~~~~~~
+
+COMPASS also supports compatible assets reconstructed with XGRIDS. These assets are post-processed into the
+NuRec format used by the COMPASS workflow, including mesh alignment and augmentation with simulation-ready
+assets available in Isaac Sim.
+
+- `Wormhole <https://huggingface.co/datasets/nvidia/PhysicalAI-Robotics-NuRec/tree/v0.2/xgrid-wormhole>`_ —
+  Embodiment: Hand-Held,
+  Sensor Rig: `XGRIDS PortalCam <https://www.xgrids.com/intl/portalcamp>`_ [2 x fish-eye cameras, 2 x front cameras, 1 x LiDAR]
+
+COMPASS Workflow
+----------------
 
-.. code-block:: bash
+The complete COMPASS workflow is maintained in the COMPASS repository:
 
-    git clone https://github.com/NVlabs/COMPASS.git
-    cd COMPASS
-    git checkout samc/support_nurec_assets_isaaclab_3.0
-    # Open docs/handbook/workflows/nurec_real2sim.md
+- **Repository:** `NVlabs/COMPASS <https://github.com/NVlabs/COMPASS>`_
+- **Branch:** ``real2sim/isaaclab_3.0``
+- **Guide:** `NuRec asset workflow <https://github.com/NVlabs/COMPASS/blob/real2sim/isaaclab_3.0/docs/handbook/workflows/nurec_real2sim.md>`_
 
-The guide covers Isaac Sim / Isaac Lab installation, COMPASS setup, downloading and
-registering NuRec Real2Sim scenes, training a residual RL specialist, evaluation,
-ONNX / TensorRT export, and ROS2 / sim-to-real deployment.
+The guide covers the COMPASS code path for training with NuRec assets generated by the Real2Sim workflow,
+including Isaac Sim and Isaac Lab setup, COMPASS installation, asset download and registration, residual RL
+specialist training, evaluation, ONNX and TensorRT export, and ROS 2 sim-to-real deployment.

pyproject.toml

@@ -188,7 +188,7 @@ reportPrivateUsage = "warning"
 skip = '*.usd,*.usda,*.usdz,*.svg,*.png,_isaac_sim*,*.bib,*.css,*/_build'
 quiet-level = 0
 # the world list should always have words in lower case
-ignore-words-list = "haa,slq,collapsable,buss,reacher,thirdparty"
+ignore-words-list = "haa,slq,collapsable,buss,reacher,thirdparty,segway"
 
 
 [tool.pytest.ini_options]