Diffusion Policy: UR5 real-robot policy evaluation

Pinned learned-policy evaluation entrypoint for the upstream UR5/UR5e real-world Push-T setup with operator control and recording. Statically reviewed source only; not run and no Hub preparation adapter.

diffusion-policy-eval-real-robot-py | Record version: source-cd7c0f1f46dce8606ebb9b2b2618811870c4d41205ce4ad6369ac5d7ac0a1b7c

Record JSON | Markdown | Pinned upstream source

Access

Fetch the pinned repository, verify this source checksum, and use upstream installation and invocation. This record does not install or execute code.

Hub preparation adapter: false. Follow the upstream setup and invocation contract.

Source and license

Repository: https://github.com/real-stanford/diffusion_policy
Revision: 5ba07ac6661db573af695b419a7947ecb704690f
Path: eval_real_robot.py
Source SHA256: cd7c0f1f46dce8606ebb9b2b2618811870c4d41205ce4ad6369ac5d7ac0a1b7c
Original authors: Cheng Chi, Siyuan Feng, Yilun Du, Zhenjia Xu, Eric Cousineau, Benjamin Burchfiel, Shuran Song
License: MIT
License scope: Selected first-party Python workflow source only. Preserve upstream copyright and per-file notices. Model weights, datasets, third-party code, robot drivers/firmware and services retain separate terms; no rights for those assets are inferred.
License SHA256: 304e99a48271e10820f71a1b86ef395c06c100d7f68dd1d308790d1064fc4d41
Hub commit: 1d6d9eb134e397d910265a8d6e7d8f257f9e8d7f

Artifact

{
  "kind": "workflow",
  "format": "python",
  "workflow_role": "policy-evaluation"
}

Requirements

{
  "python": "Python 3.9 in conda_environment_real.yaml.",
  "packages": [
    "Pinned diffusion_policy checkout",
    "Workflow-specific conda environment with PyTorch1.12.1 and CUDA toolkit11.6",
    "Configured simulator or real-robot dependencies"
  ],
  "display": "Hardware: Source moves policies to CUDA. README's Push-T setup lists UR5-CB3 or UR5e with RTDE, two RealSense D415 cameras, SpaceMouse and task-specific fixtures, on tested Ubuntu20.04.3. Weights: Requires a local checkpoint, loaded through torch.load/dill. Its configuration determines policy behavior and observation/action shape. Datasets: Consumes live robot/camera observations and writes evaluation recordings; optional dataset matching uses separately supplied local data. Services/auth: Requires robot network access through robot_ip and local camera/controller services. No cloud API key or W&B login is declared by this evaluator.",
  "execution_domain": "hardware",
  "source_imports": [
    "click",
    "cv2",
    "diffusion_policy.common.cv2_util",
    "diffusion_policy.common.precise_sleep",
    "diffusion_policy.common.pytorch_util",
    "diffusion_policy.policy.base_image_policy",
    "diffusion_policy.real_world.real_env",
    "diffusion_policy.real_world.real_inference_util",
    "diffusion_policy.real_world.spacemouse_shared_memory",
    "diffusion_policy.workspace.base_workspace",
    "dill",
    "hydra",
    "multiprocessing.managers",
    "numpy",
    "omegaconf",
    "pathlib",
    "scipy.spatial.transform",
    "skvideo.io",
    "time",
    "torch"
  ],
  "notes": "UR5/UR5e are discovery labels from the pinned setup, not Hub-tested compatibility combinations or authorization to move hardware. Code licensing does not establish model, checkpoint, dataset or service permission.",
  "declared_requirements": {
    "python": "Python 3.9 in conda_environment_real.yaml.",
    "weights": "Requires a local checkpoint, loaded through torch.load/dill. Its configuration determines policy behavior and observation/action shape.",
    "datasets": "Consumes live robot/camera observations and writes evaluation recordings; optional dataset matching uses separately supplied local data.",
    "hardware": "Source moves policies to CUDA. README's Push-T setup lists UR5-CB3 or UR5e with RTDE, two RealSense D415 cameras, SpaceMouse and task-specific fixtures, on tested Ubuntu20.04.3.",
    "external_services_and_auth": "Requires robot network access through robot_ip and local camera/controller services. No cloud API key or W&B login is declared by this evaluator.",
    "evidence": [
      {
        "anchor": "UR5's IP address",
        "line": 53
      },
      {
        "anchor": "torch.device('cuda')",
        "line": 100
      },
      {
        "anchor": "robot_ip=robot_ip",
        "line": 146
      }
    ],
    "license_scopes": {
      "code": "MIT for selected first-party workflow source.",
      "weights": "README links separately downloadable trained checkpoints but the reviewed repository text does not separately establish their license. Do not extend first-party-code MIT to weights.",
      "datasets": "README links separate task demonstration datasets and dependencies such as robomimic. Individual dataset licenses were not reviewed; code MIT does not grant dataset rights.",
      "third_party_code": "External dependencies retain their own licenses."
    },
    "interpretation": "Pinned upstream declarations only; no dependency resolution, model/data access, compatibility inference or runtime validation was performed."
  }
}

Invocation

{
  "entrypoint": "python eval_real_robot.py -i <approved-local-checkpoint> -o <local-output> --robot_ip <configured-robot-address>",
  "notes": "UR5/UR5e are discovery labels from the pinned setup, not Hub-tested compatibility combinations or authorization to move hardware."
}

Explicit compatibility

[]

Missing environment fields remain unknown. Discovery labels do not establish robot compatibility.

Evidence

Level: source_reviewed; runtime verification: not_run.

Verified exact source, applicable license and author/setup document bytes at a full Git commit; parsed the Python AST and reviewed this guarded operational entrypoint and its explicit license notices. No upstream code, installation, robot command, dataset, mesh or checkpoint was executed or loaded.

Source review and contributor reports do not establish task completion. Preserve upstream attribution and licenses.