0:000:00
Unitree G1 football
Shared by AmoghShrivastavaG1 Brunson
Policy + simulator
0:000:00
G1 BrunsonAbout this project
A Unitree G1 humanoid dribbling a regulation basketball between its legs, hand to hand, with one clean bounce through the gap between the feet on every crossover. Trained by reinforcement learning on an accurate model of the robot and ball. 44 crossover dribbles per 20-second test with no falls, 42 when guided only by its own head camera. Includes the controller (ONNX and numpy), camera perception, simulation, test results and a safety report.
- Environment
- Not specified
- Robot
- Unitree G1
- Includes
- Policy + simulator
FROM SIM TO REAL
Safety & real-world tests
01 · SubmissionFormat checked
Preferred format
02 · SimulationScreened · Review required
Automated G1 safety checks
03 · Real robotNo approval recorded
Runner video and data appear here
Robot package missing
No runner container found. Include submission.tar, or g1-runner.json with a public archive URL and SHA-256 for a large image. A model ZIP and run.sh alone cannot start in the G1 runner. setup.sh stays on the robot.
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.
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.
Review required
Compare the recorded test setup with your submitted run. Recorded findings are diagnostic; they do not yet establish a policy fault. Not approved for a real-world test.
0 tests without findings · 7 tests with findings · 5 evaluation errors · 0 unavailable or unreported scenarios
Provisional screening profile. Tests with findings need review; evaluation errors need investigation. Neither counts as a pass.
Loading builder feedback…
Basketball controller with ball tracking in its fingerprinted task scene. 12 independent 20-second dribble simulations from both authored stances; same upstream joint, torque, fall, thrash and speed checks. No walker commands, push branches, camera images or physical-robot testing.
Release: g1-screening-pr10-e93c492-v3
Evaluator revision: e93c49267a7b6b905c6666c8c70668f8ee7ac397
Policy SHA-256: 274e51d0564d27ed84e135c3762491ac88958a71bc17b29656249236bc98a27d
Submission format
Trained · Declared by submitter · Preferred · ONNX recognized
- ONNX model structure recognized: version, operations, inputs and outputs are present.
- Policy type declared as trained in arena-policy.json.
- Preferred: recognizable ONNX and an identified policy type make this submission easier to evaluate. Safety is checked separately.
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 · 2026-10-13T17:00:01.903Z
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.
Review required
Compare the recorded test setup with your submitted run. Recorded findings are diagnostic; they do not yet establish a policy fault. Not approved for a real-world test.
0 tests without findings · 7 tests with findings · 5 evaluation errors · 0 unavailable or unreported scenarios
Provisional screening profile. Tests with findings need review; evaluation errors need investigation. Neither counts as a pass.
Basketball controller with ball tracking in its fingerprinted task scene. Twelve independent 20-second dribble simulations from both authored stances; same upstream joint, torque, fall, thrash and speed checks. No walker commands, push branches, camera images or physical-robot testing.
Release: g1-screening-pr10-e93c492-v2
Evaluator revision: e93c49267a7b6b905c6666c8c70668f8ee7ac397
Policy SHA-256: 274e51d0564d27ed84e135c3762491ac88958a71bc17b29656249236bc98a27d
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.
Review required
Test setup needs review by HIM. Recorded findings are diagnostic; they do not yet establish a policy fault. Not approved for a real-world test.
0 tests without findings · 7 tests with findings · 5 evaluation errors · 0 unavailable or unreported scenarios
Provisional screening profile. Tests with findings need review; evaluation errors need investigation. Neither counts as a pass.
Basketball controller with ball tracking in its fingerprinted task scene. Twelve independent 20-second dribble simulations from both authored stances; same upstream joint, torque, fall, thrash and speed checks. No walker commands, push branches, camera images or physical-robot testing.
Release: g1-screening-pr10-e93c492-v1
Evaluator revision: e93c49267a7b6b905c6666c8c70668f8ee7ac397
Policy SHA-256: 274e51d0564d27ed84e135c3762491ac88958a71bc17b29656249236bc98a27d
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.
Review required
Test setup needs review by HIM. Recorded findings are diagnostic; they do not yet establish a policy fault. Not approved for a real-world test.
0 tests without findings · 7 tests with findings · 5 evaluation errors · 0 unavailable or unreported scenarios
Provisional screening profile. Tests with findings need review; evaluation errors need investigation. Neither counts as a pass.
Basketball controller with ball tracking in its fingerprinted task scene. Twelve independent 20-second dribble simulations from both authored stances; same upstream joint, torque, tracking, fall and sustained-speed checks. No walker commands, push branches, camera images or physical-robot testing.
Release: g1-screening-pr6-47cd947-v4
Evaluator revision: 47cd9479d5dda1598e12ec94649e6e7bc1468d63
Policy SHA-256: 274e51d0564d27ed84e135c3762491ac88958a71bc17b29656249236bc98a27d
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.
Check incomplete
Screening incomplete: findings recorded in 12 scenarios, 5 evaluation errors, 0 unavailable or unreported scenarios.
0 tests without findings · 7 tests with findings · 5 evaluation errors · 0 unavailable or unreported scenarios
Provisional screening profile. Tests with findings need review; evaluation errors need investigation. Neither counts as a pass.
Basketball controller with ball tracking in its fingerprinted task scene. Twelve independent 20-second dribble simulations from both authored stances; same upstream joint, torque, tracking, fall and sustained-speed checks. No walker commands, push branches, camera images or physical-robot testing.
Release: g1-screening-pr6-47cd947-v2
Evaluator revision: 47cd9479d5dda1598e12ec94649e6e7bc1468d63
Policy SHA-256: 274e51d0564d27ed84e135c3762491ac88958a71bc17b29656249236bc98a27d
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.
Original diagnostic: This policy needs a supported safety adapter. Declare safety_adapter: g1-walker-99-v1 only when its observation/action semantics match that contract.
Neural controller only; scripted behavior is not screened.
Release: g1-screening-pr6-47cd947-v1
Evaluator revision: 47cd9479d5dda1598e12ec94649e6e7bc1468d63
Policy SHA-256: 274e51d0564d27ed84e135c3762491ac88958a71bc17b29656249236bc98a27d
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.
submission_v9.zip · SHA-256 274e51d0564d27ed84e135c3762491ac88958a71bc17b29656249236bc98a27dWhat’s included
Policy + simulator · Result video · Project ZIP
Builder-provided run command
./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
submission_v9.zip · 24.4 MB
SHA-256 274e51d0564d27ed84e135c3762491ac88958a71bc17b29656249236bc98a27d
trained.mp4 · MP4