Open-IO/Unified-Inertial-Encoder

A Unified Inertial Encoder for Human and Humanoid Motion: Checkpoint

Project Page | Code

One encoder, trained on human motion and kinematically retargeted G1 motion, transfers zero-shot to a physical Unitree G1. This repository holds the checkpoint behind the paper's "Ours" results.

Files

checkpoints/unified_encoder.ckpt   model weights (EMA, bf16, 55.6M parameters)
.hydra/                           Hydra config of the training run (experiment=exp15_full_train_C)

Keep .hydra/ next to checkpoints/, because the code rebuilds the model from it. The checkpoint holds weights only, without optimizer state, so it supports evaluation and fine-tuning ('meta.resume_from=<CKPT>' meta.resume_full_state=false), not exact resumption of the training run.

Quick Usage

With the code installed:

RUN="${FOUNDATIONIMU_EXP_ROOT:-experiments}/unified-inertial-encoder"
hf download Open-IO/Unified-Inertial-Encoder --local-dir "$RUN"
hf download Open-IO/humanoid-g1-odometry --repo-type dataset \
    --local-dir "$FOUNDATIONIMU_CACHE_ROOT/humanoid_superodom_clips_v2"

python -m src.eval_foundation \
    --ckpt "$RUN/checkpoints/unified_encoder.ckpt" \
    --data_from "$RUN" \
    --dataset Humanoid_SuperOdom_NPZ_Processed_Language \
    --json real_g1.json

src.eval_foundation needs a CUDA GPU. See the code repository for the other datasets.

Results

Scores reported in the paper. AVE is the average velocity error (m/s). ATE_GT and ATE_Pred are trajectory errors (m) using ground-truth rotation and rotation preintegrated from the gyroscope.

Dataset	AVE	ATEGT	ATEPred
Nymeria	0.026	2.468	18.20
Natural Motion	0.049	7.456	50.54
BONES-Seed (Human)	0.031	0.113	0.148
BONES-Seed (G1)	0.024	0.101	0.127
Real-Trajectory (G1)	0.099	3.153	11.50

Real-G1 clips are never used for gradient training, but their scores informed the selection of this checkpoint.

Citation

@misc{chen2026unifiedinertial,
  title={A Unified Inertial Encoder for Human and Humanoid Motion},
  author={Chen, Yutian and Zhao, Shibo and Duan, Rocky and Liu, Karen and
          Sferrazza, Carmelo and Shi, Guanya and Qiu, Yuheng and Sreenath, Koushil},
  year={2026},
  url={https://unified-inertial-encoder.github.io/}
}