OpenMHSindependent draft 0.9
Playground
Open menu

Robots · Other devices

UR3 pick-and-place planner (Unity object pose estimation demo)

UR3 pick-and-place planner (Unity object pose estimation demo), adapted from unity-technologies/robotics-object-pose-estimation. It runs plan_pick_and_place. plan_pick_and_place: plan (never execute) the five UR3 pick-and-place trajectories; executed is false. A command: it changes the node's shared planner, so never call while Unity plans; a zero quaternion is refused. A simulator: the market serves it with a stand-in that needs no simulator install.

simulatedRisk R1Apache-2.0contract_checkedserved on the fake backend
openai4s lab add robots/unity-technologies__robotics-object-pose-estimation
All install options REFERENCE.md Upstream repository Registry record

Install

Three ways to run this device. Each one serves its fake backend: no instrument, no simulator install and no upstream checkout.

OpenAI4S (one command)

shell
openai4s lab add robots/unity-technologies__robotics-object-pose-estimation

Installs the device into the OpenAI4S Lab on its fake backend and starts it. First time? See setup below.

Or, in the workbench, open the Lab tab → Market → Install.

Standalone MHS endpoint

shell
git clone --depth 1 https://github.com/PKU-YuanGroup/OpenMHS.git && cd OpenMHS
PYTHONPATH=MHS/sdk/src python3 -m mhs serve robots/unity-technologies__robotics-object-pose-estimation --port 7400
# in a second terminal, from the same directory:
PYTHONPATH=MHS/sdk/src python3 -m mhs describe --endpoint http://127.0.0.1:7400

Serves the device as an MHS endpoint on port 7400 from an OpenMHS clone (Python 3.10 or later, standard library only); describe prints what it offers.

Any MCP host (Claude Desktop, Cursor, …)

mcp configuration
{
  "mcpServers": {
    "robotics-object-pose-estimation": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "robots/unity-technologies__robotics-object-pose-estimation",
        "--mcp"
      ],
      "env": {
        "PYTHONPATH": "/path/to/OpenMHS/MHS/sdk/src"
      }
    }
  }
}

Add this server to the host's MCP configuration and replace /path/to/OpenMHS with the path of your OpenMHS clone. The host starts the server and talks to it on stdin and stdout.

What it does

Measures

Nothing declared.

Adjusts

Nothing declared.

Actions

plan_pick_and_place
Plan (never execute) the five UR3 pick-and-place trajectories; executed is false. A command: it changes the node's shared planner, so never call while Unity plans; a zero quaternion is refused.

Names as the driver declares them. Units, limits and the safety declaration are in the package's REFERENCE.md.

First-time setup

The OpenAI4S workbench with the OpenMHS lab, from a source checkout:

shell
# OpenAI4S workbench with the OpenMHS lab (source checkout)
git clone --recursive https://github.com/PKU-YuanGroup/OpenAI4S.git
cd OpenAI4S && ./setup.sh && source .venv/bin/activate
openai4s lab add robots/unity-technologies__robotics-object-pose-estimation
openai4s serve        # open the Lab tab

The standalone endpoint and the MCP server need only an OpenMHS clone and Python 3.10 or later. More in the market's getting-started guide and on the OpenAI4S host page.

Source and evidence

Pinned commit
45156479bee5
Licence
Apache-2.0
Stars
352
Evidence
contract_checked on the fake backend
Backends
fake

The driver package MHS/drivers/robots/unity-technologies__robotics-object-pose-estimation wraps the upstream code at the pinned commit. Its REFERENCE.md documents the full contract: every value, action, unit, limit and the safety declaration.