SAVRN
Search Contact SAVRN

Open-weight model

g1_depth_dodge

by Martino Russi nepyope/g1_depth_dodge

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.

Parameters
Context
Weights152.8 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads

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.

Weights4 files · 152.8 MB
Configuration1 file · 3.7 KB
Documentation1 file · 1.0 KB
Repository1 file · 1.5 KB
Every file
FileTypeSizeSHA-256
actor.onnxWeights64.0 MB d51c90007160
perception.onnxWeights2.5 MB 8610ee92c5cb
sonic_plain.onnxWeights64.0 MB dbf324b5bfb6
theia_image.onnxWeights22.4 MB 127c726b01bd
manifest.jsonConfiguration3.7 KB
README.mdDocumentation1.0 KB
.gitattributesRepository1.5 KB

License and Download

License
apache-2.0
Access
Open weights, no gate
Download size
152.8 MB
Download from Martino Russi

Released by Martino Russi through its official repository on Hugging Face. Read the license.

Memory Requirements

PrecisionWeights in memory
As published152.8 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.