Frozen SONIC whole-body controller + seven rank-16 LoRAs on the decoder, conditioned on a 128-d percept from a head depth camera (Theia-Tiny tokens + temporal adapter). PPO, iteration 4000. Consumed by lerobot's DepthDodgeController for the Unitree G1.
Model Card
By Martino Russi, published under apache-2.0, revision 10e207cb734a.
Frozen SONIC whole-body controller + seven rank-16 LoRAs on the decoder, conditioned on a 128-d percept from a head depth camera (Theia-Tiny tokens + temporal adapter). PPO, iteration 4000. Consumed by lerobot's DepthDodgeController for the Unitree G1. Camera contract: 64x96 optical-Z depth in metres, 45 deg vertical FOV, 0 deg pitch, valid 0.2-6 m, 25 Hz. See manifest.json for the full training config.
Read Martino Russi's full model card
G1 depth dodgeball on frozen SONIC (ONNX deploy)
Frozen SONIC whole-body controller + seven rank-16 LoRAs on the decoder, conditioned on a
128-d percept from a head depth camera (Theia-Tiny tokens + temporal adapter). PPO, iteration 4000.
Consumed by lerobot's DepthDodgeController for the Unitree G1.
| file | inputs | outputs |
|---|---|---|
theia_image.onnx |
image uint8 [B,224,224] (depth mapped 255 near .. 1 far, 0 invalid) |
tokens [B,197,192] fp32 |
perception.onnx |
depth_tokens fp32 [1,16,197,192] (16-frame ring at 25 Hz, fp16-rounded) |
percept [1,128] |
actor.onnx |
tokenizer[1,640], policy[1,930], conditioning[1,768] = concat(tokenizer, percept) |
actions[1,29] SONIC-normalized PD residuals, MuJoCo joint order |
Camera contract: 64x96 optical-Z depth in metres, 45 deg vertical FOV, 0 deg pitch, valid 0.2-6 m, 25 Hz.
See manifest.json for the full training config.
Identity and Version
- Repository
- nepyope/g1_depth_dodge
- Publisher
- Martino Russi
- Task
- Not stated by the source
- Modality
- Other
- Library
- lerobot
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 10e207cb734a6c3edf792d4995ca59ae4641bf29
- First published
- 2026-09-18
- Last updated
- 2026-09-18
Files and Weights
7 files, 152.8 MB in total. The weights are 4 files totalling 152.8 MB in onnx.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| actor.onnx | Weights | 64.0 MB | d51c90007160 |
| perception.onnx | Weights | 2.5 MB | 8610ee92c5cb |
| sonic_plain.onnx | Weights | 64.0 MB | dbf324b5bfb6 |
| theia_image.onnx | Weights | 22.4 MB | 127c726b01bd |
| manifest.json | Configuration | 3.7 KB | — |
| README.md | Documentation | 1.0 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 152.8 MB
Released by Martino Russi through its official repository on Hugging Face. Read the license.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 152.8 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About g1_depth_dodge
Can I use g1_depth_dodge commercially?
Yes. g1_depth_dodge is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.