0:000:00
RIGHT HAND RULE V2 - Maze by touch, joints + IMU
Shared by Marc DonoviciRallyForge v3 — Real Rallies and Measured-State Control
Policy + simulator
0:000:00
RallyForge v3 — Real Rallies and Measured-State ControlAbout this project
Genuine guarded rallies:2.58 vs1.86 mean legal shots/50 paired starts,unsafe0/50. Exact-state research best14;unsafe1/50. RGB-D/contact odometry:49/50 standard,31/50 wide;live base translation withheld,ideal IMU/calibrated station. ARM64 standby artifact:one20s builder pass;failed repeats and all counterfactuals retained. Source,video,traces,13 tests and attribution. Extends willli/Alpslee,Unitree and NVIDIA work. Local simulation;full task/hardware unqualified.
- Environment
- MuJoCo
- Robot
- Unitree G1
- Includes
- Policy + simulator
FROM SIM TO REAL
Safety & real-world tests
01 · SubmissionFormat checked
Archive and policy files
02 · SimulationSimulation not run
Prepare a compatible export below
03 · Real robotNo approval recorded
Runner video and data appear here
Image reference provided · unverified
Container reference recorded; bytes, architecture, entrypoint and execution are not verified. Required inputs need qualification: camera. The standard runner does not supply camera images or lidar; base state requires a configured qualified source.
Container simulation and hardware qualification are separate. Arena’s current automatic model screening does not execute the submitted image, its entrypoint, ROS interface or camera pipeline.
Inspected file: g1-runner.json
Builder-provided archive: Open external image download (unverified)
Builder-declared image SHA-256: 96a370ac048731d57872a1f22b4c88b573785c45751aa4962eb21501f6864e13
Declared inputs: joint_state, imu, camera
Before a robot run, verify the image digest and run that same container through the repository’s safety-enabled simulator. Retain the reports and traces. Builder-provided reports require independent verification; they never grant automatic hardware approval.
Required: linux/arm64, installed dependencies, one entrypoint, the 29-slot safety protocol and abort handling. Camera/lidar are not standard inputs; base state needs qualification. setup.sh belongs on the robot.
Pinned team requirementsContract revision: e93c49267a7b6b905c6666c8c70668f8ee7ac397
Preferred means the submission format is easy to process. It says nothing about safety.
This automated check records simulation findings. Even a complete run with no findings does not award a Safe or Sim2Real Ready tag. The current screening system requires separate hardware approval; that approval is not provided by this check.
Real-world validated appears only after a runner publishes a successful physical test. It describes that test, not a guarantee for future runs.
Safety check
Model screening only. This report does not verify the submitted container’s startup, safety messaging or sensor inputs. See the G1 runner package requirements above.
Simulation not run · compatibility blocked
Arena could not start the safety simulation for this upload. No safety result was established. Follow the preparation steps below.
Loading builder feedback…
Original diagnostic: Multiple policy declarations are ambiguous.
No simulation ran unless this report records a supported controller and scenario coverage.
Release: g1-screening-pr10-e93c492-v3
Evaluator revision: e93c49267a7b6b905c6666c8c70668f8ee7ac397
Policy SHA-256: bdb800fa083160f93ef26ac74dbbbfb209453a1a5317bb00ff20ac267bcddf8b
Submission format
Trained · Automatically detected · ONNX recognized
Include only one arena-policy.json so the policy type and model are unambiguous.
- Include only one arena-policy.json so the policy type and model are unambiguous.
- ONNX model structure recognized: version, operations, inputs and outputs are present.
- Likely trained, based on model parameters. Training provenance is not verified.
- Other formats can still be submitted. Preferred only describes the initial submission standard.
Static inspection only; this does not establish training provenance or hardware safety.
An identified policy type and a recognizable ONNX model help us process submissions consistently. Preferred does not mean Sim2Real Ready. Other formats are welcome.
For the clearest result, include an ONNX model and an arena-policy.json file beside it:
{"policy_type":"trained","model":"policy.onnx"}Use scripted for hand-authored behavior. The model path is relative to this file. The first validator checks model structure up to 16 MB; it does not run the model.
Validator: arena-validator-v2-g1-container · 2026-11-09T02:29:42.068Z
No real-world test recorded in Arena yet. Video, results, and run data will appear here.
Get started
Download the project files to explore, reproduce, or build on this work. Inspect the builder’s code before running it in your environment.
RallyForge-v3.zip · SHA-256 bdb800fa083160f93ef26ac74dbbbfb209453a1a5317bb00ff20ac267bcddf8bWhat’s included
Policy + simulator · Result video · Project ZIP
Builder-provided run command
bash run.shEvaluation details
Recorded screening and hardware evidence are shown in the real-world test section above.
Limitations
This project is shared by its builder. Simulation results do not establish real-world safety. Review the source, dependencies, licensing, and hardware requirements before use.
Files & contents
RallyForge-v3.zip · 62.3 MB
SHA-256 bdb800fa083160f93ef26ac74dbbbfb209453a1a5317bb00ff20ac267bcddf8b
result-v3.mp4 · MP4