Downloads · 30 days
0
hyunho7979/sonic-capoeira-v8
sonic-capoeira-v8 is a reinforcement learning model from hyunho7979. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product.
SONIC Capoeira V8 is a Unitree G1 whole-body control policy fine-tuned from NVIDIA SONIC for a dynamic, hand-supported capoeira kick with landing recovery.
Downloads · 30 days
0
Access
Public
Updated Aug 16, 2026
Repo size
91 MB
Likes
0
Public
Click a slice to open those files.
.onnx91 MB · 100%
From the Hugging Face model README
SONIC Capoeira V8 is a Unitree G1 whole-body control policy fine-tuned from NVIDIA SONIC for a dynamic, hand-supported capoeira kick with landing recovery.
model_step_000025_encoder.onnx: observation encodermodel_step_000025_decoder.onnx: action decoderobservation_config.yaml: deployment observation configurationparity.json: PyTorch-to-ONNX numerical parity reportThe paired encoder and decoder must be used together with the supplied observation configuration and the matching motion reference dataset.
The policy was fine-tuned in Isaac Sim with landing-contact, capture-point, two-foot-support, joint-speed, knee-torque-reserve, and final-upright rewards. It completed 112/112 Isaac Sim evaluations across nominal and randomized profiles. ONNX parity maximum absolute error was 0 for the encoder and 1.6689300537109375e-6 for the decoder.
In the official C++ MuJoCo closed loop, the selected checkpoint passed the initial safety gate and executed the full 467-frame motion in 10/10 trials. Strict final post-landing stabilization succeeded in 3/10 trials.
This is a simulation research artifact. It is not real-robot ready and must not be deployed on a physical G1 without additional safety validation, hardware limits, supervision, and a reliable recovery controller.
https://github.com/danniely/ultimate-bots-G1
https://huggingface.co/datasets/hyunho7979/sonic-capoeira-v8