---
license: apache-2.0
tags: [lerobot, unitree_g1, sonic, dodgeball, depth]
---
# 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.