# Genesis Panda cartesian ik

Genesis Panda cartesian ik. Bounded, source-pinned simulation with an explicit task contract and retained fixed-case outcomes.

Record version: `1.0.0` · Hub commit: `f97266a5cdd2c600cd376397a54892f08290df20`

## Executable interface

```json
{
  "version": "1",
  "kind": "controller",
  "abstraction_level": 1,
  "execution_domain": "simulation",
  "language": "python",
  "input_transport": "json_file_or_inline",
  "output_transport": "json_stdout",
  "output_selector": "outputs",
  "conventions": {
    "linear_unit": "m",
    "angular_unit": "rad",
    "time_unit": "s",
    "coordinate_frame": "right_handed_world_xyz; +z_up",
    "joint_order": "joint1, joint2, joint3, joint4, joint5, joint6, joint7; finger errors are separate metric distances",
    "quaternion_order": "not_used"
  },
  "input_schema": {
    "type": "object",
    "required": [
      "seed",
      "target_offset_m"
    ],
    "properties": {
      "seed": {
        "type": "integer",
        "minimum": 0,
        "maximum": 10000
      },
      "target_offset_m": {
        "type": "array",
        "minItems": 3,
        "maxItems": 3,
        "items": {
          "type": "number",
          "minimum": -0.06,
          "maximum": 0.06
        },
        "x-unit": "m",
        "x-frame": "right_handed_world_xyz; +z_up"
      }
    },
    "additionalProperties": false
  },
  "output_schema": {
    "type": "object",
    "required": [
      "arm_joint_positions_rad",
      "target_arm_joint_positions_rad",
      "finger_error_m",
      "movement_m",
      "max_joint_error_rad",
      "cuda_simulation",
      "steps",
      "final_xyz_m",
      "target_xyz_m",
      "error_m"
    ],
    "properties": {
      "arm_joint_positions_rad": {
        "type": "array",
        "minItems": 7,
        "maxItems": 7,
        "items": {
          "type": "number",
          "minimum": -10,
          "maximum": 10
        },
        "x-unit": "rad",
        "x-order": [
          "joint1",
          "joint2",
          "joint3",
          "joint4",
          "joint5",
          "joint6",
          "joint7"
        ]
      },
      "target_arm_joint_positions_rad": {
        "type": "array",
        "minItems": 7,
        "maxItems": 7,
        "items": {
          "type": "number",
          "minimum": -10,
          "maximum": 10
        },
        "x-unit": "rad",
        "x-order": [
          "joint1",
          "joint2",
          "joint3",
          "joint4",
          "joint5",
          "joint6",
          "joint7"
        ]
      },
      "finger_error_m": {
        "type": "number",
        "minimum": 0,
        "maximum": 1,
        "x-unit": "m"
      },
      "movement_m": {
        "type": "number",
        "minimum": 0,
        "maximum": 50,
        "x-unit": "m"
      },
      "max_joint_error_rad": {
        "type": "number",
        "minimum": 0,
        "maximum": 50,
        "x-unit": "rad"
      },
      "cuda_simulation": {
        "type": "boolean"
      },
      "steps": {
        "type": "integer",
        "minimum": 1,
        "maximum": 1000
      },
      "final_xyz_m": {
        "type": "array",
        "minItems": 3,
        "maxItems": 3,
        "items": {
          "type": "number",
          "minimum": -20,
          "maximum": 20
        },
        "x-unit": "m",
        "x-frame": "right_handed_world_xyz; +z_up"
      },
      "target_xyz_m": {
        "type": "array",
        "minItems": 3,
        "maxItems": 3,
        "items": {
          "type": "number",
          "minimum": -20,
          "maximum": 20
        },
        "x-unit": "m",
        "x-frame": "right_handed_world_xyz; +z_up"
      },
      "error_m": {
        "type": "number",
        "minimum": 0,
        "maximum": 50,
        "x-unit": "m"
      }
    },
    "additionalProperties": false
  },
  "preconditions": [
    "Use the exact recorded source, Linux Python 3.11 environment and pinned direct packages.",
    "No physical robot, network actuation or external robot credentials."
  ],
  "postconditions": [
    "All reported checks must be true and all output numbers finite.",
    "Success covers the declared goal and frozen cases, not arbitrary tasks or physical hardware."
  ],
  "failure_codes": [
    "invalid_input_or_environment",
    "execution_failed",
    "task_failed"
  ],
  "composition": {
    "depends_on": [],
    "automatic_frame_conversion": false,
    "automatic_hardware_execution": false
  },
  "origin_reference_ids": [
    "genesis-examples-examples-rigid-ik-franka-py"
  ],
  "origin_relationship": "prepared_from_the_same_pinned_model; inspect the declared controller and goal; no physical compatibility is inferred"
}
```



## Exact environment

| Runtime | Robot | Controller | Observation | OS | Python | Evidence |
| --- | --- | --- | --- | --- | --- | --- |
| genesis 1.4.4 | panda | cartesian_ik | privileged_simulator_state | linux x86_64 | >=3.11,<3.12 | task_complete |

Privileged simulator observations and goal/state feedback. No physical sensor validation.

Compatibility status: **hub_verified**. An environment match does not establish task completion. Runtime verification: **task_complete**.

## Source and license

- Repository: https://github.com/Genesis-Embodied-AI/genesis-world
- Source commit: `a5c4e9a73aca221fa26e611281f2696c5f8b0ca8` (no tag)
- Original authors: Original genesis-world contributors; preserve all pinned source and asset notices
- License: [Apache-2.0](https://github.com/Genesis-Embodied-AI/genesis-world/blob/a5c4e9a73aca221fa26e611281f2696c5f8b0ca8/LICENSE)
- Source archive SHA256: `851d0970b921ee1b5182f62c544f432600153efccc127db059d5f5e46d9ac719`
- Upstream files: `LICENSE`, `pyproject.toml`, `examples/rigid/ik_franka.py`, `genesis/__init__.py`, `genesis/engine/entities/rigid_entity/rigid_entity.py`, `genesis/assets/xml/franka_emika_panda/panda.xml`
- Upstream contribution rules: https://github.com/Genesis-Embodied-AI/genesis-world

## Find, inspect, prepare

```sh
python /PATH_TO_SKILL/scripts/rsh.py find "simulation" --runtime genesis --runtime-version 1.4.4 --robot panda --json
python /PATH_TO_SKILL/scripts/rsh.py inspect genesis-panda-cartesian-ik --json
python /PATH_TO_SKILL/scripts/rsh.py prepare genesis-panda-cartesian-ik --project ./experiment --expected-source-commit a5c4e9a73aca221fa26e611281f2696c5f8b0ca8 --expected-record-version 1.0.0 --plan --json
```

Remove `--plan` to download the checksum-verified pinned source and create an isolated project environment. Preparation returns the remaining configuration. Dependency installation is an explicit `--install-deps` step; it can execute package build hooks. Robot simulation is a separate command returned by prepare, never run by find/inspect.

Direct package pins: `DracoPy==2.2.0`, `OpenEXR==3.5.2`, `Pillow==11.3.0`, `PyGEL3D==0.8.2`, `PyOpenGL==3.1.10`, `av==18.1.0`, `coacd==1.0.14`, `fast_simplification==0.2.0`, `freetype-py==2.5.1`, `frozendict==2.4.7`, `genesis-world==1.4.4`, `gs-madrona==0.0.10`, `libigl==2.6.3`, `moviepy==2.2.1`, `mujoco==3.16.0`, `numba==0.68.0`, `numpy==1.26.4`, `opencv-python==4.11.0.86`, `psutil==7.2.2`, `py-cpuinfo==9.0.0`, `pycollada==0.9.3`, `pydantic==2.14.1`, `pyglet==2.1.19`, `pygltflib==1.16.0`, `pymeshlab==2025.7.post1`, `pysplashsurf==0.14.1.0`, `quadrants==1.3.3`, `rtree==1.4.1`, `scikit-image==0.26.0`, `tetgen==0.8.2`, `torch==2.8.0`, `trimesh==5.1.1`, `vtk==9.7.1`, `xacro==2.1.1`, `z3-solver==4.15.4.0`, `zstandard==0.25.0`.

Direct runtime versions are pinned and measured. The receipt retains the complete environment freeze; prepare records the installed environment. System drivers are separate host requirements. Some pinned dependencies ship source distributions; explicit dependency installation and build tools may be required.

Hardware: Linux x86_64; CUDA GPU; see retained receipt for the exact host environment.

Rendering: Headless. EGL libraries are required for MuJoCo imports; PushT uses SDL dummy video. No interactive display..

External API keys: none.

## Invocation contract

Entrypoint: `python run.py`.

```json
{
  "argv": [
    "{python}",
    "{recipe_dir}/run.py",
    "--source-dir",
    "{source_dir}",
    "--example"
  ],
  "inputs": {
    "seed": 0,
    "target_offset_m": [
      0.03,
      0,
      0
    ]
  },
  "outputs": {
    "format": "single JSON object",
    "payload_selector": "outputs",
    "schema": {
      "type": "object",
      "required": [
        "arm_joint_positions_rad",
        "target_arm_joint_positions_rad",
        "finger_error_m",
        "movement_m",
        "max_joint_error_rad",
        "cuda_simulation",
        "steps",
        "final_xyz_m",
        "target_xyz_m",
        "error_m"
      ],
      "properties": {
        "arm_joint_positions_rad": {
          "type": "array",
          "minItems": 7,
          "maxItems": 7,
          "items": {
            "type": "number",
            "minimum": -10,
            "maximum": 10
          },
          "x-unit": "rad",
          "x-order": [
            "joint1",
            "joint2",
            "joint3",
            "joint4",
            "joint5",
            "joint6",
            "joint7"
          ]
        },
        "target_arm_joint_positions_rad": {
          "type": "array",
          "minItems": 7,
          "maxItems": 7,
          "items": {
            "type": "number",
            "minimum": -10,
            "maximum": 10
          },
          "x-unit": "rad",
          "x-order": [
            "joint1",
            "joint2",
            "joint3",
            "joint4",
            "joint5",
            "joint6",
            "joint7"
          ]
        },
        "finger_error_m": {
          "type": "number",
          "minimum": 0,
          "maximum": 1,
          "x-unit": "m"
        },
        "movement_m": {
          "type": "number",
          "minimum": 0,
          "maximum": 50,
          "x-unit": "m"
        },
        "max_joint_error_rad": {
          "type": "number",
          "minimum": 0,
          "maximum": 50,
          "x-unit": "rad"
        },
        "cuda_simulation": {
          "type": "boolean"
        },
        "steps": {
          "type": "integer",
          "minimum": 1,
          "maximum": 1000
        },
        "final_xyz_m": {
          "type": "array",
          "minItems": 3,
          "maxItems": 3,
          "items": {
            "type": "number",
            "minimum": -20,
            "maximum": 20
          },
          "x-unit": "m",
          "x-frame": "right_handed_world_xyz; +z_up"
        },
        "target_xyz_m": {
          "type": "array",
          "minItems": 3,
          "maxItems": 3,
          "items": {
            "type": "number",
            "minimum": -20,
            "maximum": 20
          },
          "x-unit": "m",
          "x-frame": "right_handed_world_xyz; +z_up"
        },
        "error_m": {
          "type": "number",
          "minimum": 0,
          "maximum": 50,
          "x-unit": "m"
        }
      },
      "additionalProperties": false
    }
  }
}
```

Success: All declared goal and finite-state checks pass; exit 0 with task_complete. CUDA dynamic simulation after reset. PD tracking below 0.04 rad and nontrivial hand motion; IK variant also requires final hand position error below 15 mm. Source example kinematic visualization is adapted to real simulation stepping.

Timeout: 600 seconds. Terminate the adapter at the recorded timeout. No physical hardware is opened.

Failures: Invalid input or source checksum; Different pinned package version; Unavailable runtime/driver; Goal not reached within bounded steps.

## Actual evidence

All 3 frozen cases completed against this exact adapter and source.

Reviewer: Hub finite-case Lambda execution harness · 2026-10-20.

Commands/checks actually performed:

- python tools/verify_runtime_expansion.py --backend genesis --source-cache SOURCE_CACHE --output OUTPUT

Submitted evidence and hub verification remain separate. A schema check, PR creation or merge does not establish task success or publication.

## Reusable fixes

Change the runtime expansion manifest/template, regenerate, and rerun all frozen cases. Preserve source/model/checkpoint licenses and distinguish simulation from hardware.

# Genesis Panda cartesian ik

Genesis Panda cartesian ik. Bounded, source-pinned simulation with an explicit task contract and retained fixed-case outcomes.

CUDA dynamic simulation after reset. PD tracking below 0.04 rad and nontrivial hand motion; IK variant also requires final hand position error below 15 mm. Source example kinematic visualization is adapted to real simulation stepping.

Source and model terms: Apache-2.0. The Hub wrapper is MIT. See the record for input JSON, exact environment, frozen execution receipts and preparation requirements.