Document Metatron v1 browser exports and model license

NOTICE.txt

@@ -0,0 +1,13 @@
+Licensed by NVIDIA Corporation under the NVIDIA Open Model License.
+Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+
+This notice covers the Metatron G1 ONNX exports in demo/model.onnx and
+racer/network.onnx. See LICENSE.pdf for the complete agreement.
+
+The two artifacts contain the same learned policy in different runtime graph
+layouts. They are not the separate SAMP scene-interaction policy.
+
+Robot assets, motion datasets, reference clips and third-party runtime software
+are not included here. Their respective licenses and permissions remain
+separate from the model license. This repository grants no rights to those
+separate assets, including standalone redistribution of demo-only motion clips.

README.md

@@ -0,0 +1,121 @@
+---
+license: other
+license_name: nvidia-open-model-license
+license_link: https://huggingface.co/nvidia/metatron-browser/blob/main/LICENSE.pdf
+language:
+- en
+library_name: onnx
+tags:
+- robotics
+- reinforcement-learning
+- humanoid
+- onnx
+- metatron
+---
+
+# Metatron v1 — G1 Browser Exports
+
+## Overview
+
+ONNX inference exports of the Metatron G1 walking/recovery policy used by the
+Metatron browser demo and G1 Racer. Both files use the same learned policy
+weights, with different runtime interfaces. They are **not interchangeable**.
+This repository does not include the separate SAMP scene-interaction policy.
+
+| Field | Value |
+| --- | --- |
+| Robot | Unitree G1, 29 controlled joints |
+| Model | Conditional generative control policy with a gated recovery adapter |
+| Inference | Deterministic learned prior; FP32 |
+| Format | ONNX |
+| Integration | ONNX Runtime Web with WebGPU or WebAssembly |
+
+## Intended Use
+
+Interactive humanoid control, locomotion and recovery evaluation with the
+matching browser applications. The applications provide physics, observations,
+task goals and control logic; the ONNX files alone are not complete demos.
+
+Metatron supports deployment workflows beyond the browser, including other
+simulators and real G1 robots. These particular browser exports require their
+matching observation and control interfaces: compatibility is not a safety
+certification or a claim that these exact files have been validated on hardware.
+
+## Artifacts
+
+| File | Interface | Size |
+| --- | --- | --- |
+| `demo/model.onnx` | Single-robot pipeline, including observation processing and action conversion | 397,088,354 bytes |
+| `racer/network.onnx` | Six-robot batched network; requires G1 Racer's separate observation processing | 396,370,481 bytes |
+
+The Racer export changes graph organization and batching, not learned weights.
+Neither artifact is a resumable training checkpoint. Runtime code, robot assets,
+motion clips and application configuration are distributed separately.
+
+## Inputs and Outputs
+
+The demo pipeline consumes current G1 state, eight historical state samples,
+raw-action history, ground height, masked future pose/style/velocity goals and
+an explicit `recovery_enabled` input. It returns joint PD targets (`action`),
+PD gains (`stiffness`, `damping`) and `raw_action` for history feedback.
+Recovery targets and the recovery gate remain runtime inputs, not baked goals.
+
+G1 Racer computes observations outside the neural graph and evaluates all six
+robots in one batch. Its network exposes `action` and `raw_action`; controller
+parameters come from the paired runtime. Do not feed raw demo inputs directly
+to this network or change its batch size without rebuilding and validating it.
+
+Preserve the paired application's joint/body ordering, quaternion convention,
+history ordering, normalization, target masks, control rate and action mapping.
+Use the matching runtime manifest and ONNX tensor signatures for exact layouts.
+
+## Runtime Support and Validation
+
+The browser integrations use MuJoCo WASM for simulation and ONNX Runtime Web for
+inference. WebGPU is recommended on capable devices; CPU/WASM is a fallback and
+does not guarantee real-time six-robot operation. GPU drivers, browsers and
+hardware affect startup time and throughput.
+
+The demo export's recorded native-to-ONNX checks have maximum absolute errors
+below 3.1e-6 across the checked outputs with recovery enabled and disabled.
+These are numerical export checks, not task-success or real-robot benchmarks.
+Racer's paired application also runs action-parity fixtures at startup.
+
+For reproducibility, pin downloads to a repository commit rather than `main`.
+Public browser delivery requires anonymous access to the files; never embed a
+Hugging Face access token in client-side code.
+
+## Limitations and Safety
+
+- Recovery, balance and tracking can fail, especially outside the evaluated
+  states, terrain and command distribution.
+- Game launch assists, low-gravity zones and respawns are application mechanics,
+  not capabilities guaranteed by the learned policy or physical robot.
+- The model is not a collision-avoidance system or a safety controller.
+- Hardware use requires independent validation, appropriate joint/torque limits,
+  supervised testing, and an emergency-stop mechanism.
+- These exports are not a complete training-reproduction package. No training
+  dataset or training checkpoint is included.
+
+## License and Asset Rights
+
+Model terms: [NVIDIA Open Model License Agreement](LICENSE.pdf), with the
+required attribution in [NOTICE.txt](NOTICE.txt). The complete agreement
+governs; this card does not replace or extend it.
+
+Model licensing does not grant rights to motion datasets, recovery reference
+clips, robot meshes, game assets or third-party runtime software. None of those
+assets is included in this model repository. Obtain them through their
+respective distributions and follow their separate terms. Permission to include
+a clip inside a demo or game does not imply permission to redistribute that
+clip as a standalone dataset.
+
+This repository is currently a private integration preview. Adding these
+documents does not establish public-release clearance or change the release
+status of the associated applications and assets.
+
+## References
+
+- [ProtoMotions](https://github.com/NVlabs/ProtoMotions)
+- [ProtoMotions documentation](https://protomotions.github.io/)
+- [NVIDIA Open Model License](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/)