OpenMHSindependent draft 0.9
Playground
Open menu

Robots · Mobile robots

AuNa Gazebo Ackermann race car

AuNa Gazebo Ackermann race car, adapted from harunteper/auna. It reads read_velocity_source; runs select_velocity_source, publish_teleop_velocity and stop_velocity_source. select_velocity_source: select one configured multiplexer input source. Selecting OFF stops forwarding and makes the timer publish zero commands; selecting a motion source can immediately re-publish that source's cached last command. A simulator: the market serves it with a stand-in that needs no simulator install.

simulatedRisk R2MITcontract_checkedserved on the fake backend
openai4s lab add robots/harunteper__auna
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/harunteper__auna

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/harunteper__auna --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": {
    "auna": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "robots/harunteper__auna",
        "--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

  • read_velocity_source

Adjusts

Nothing declared.

Actions

select_velocity_source
Select one configured multiplexer input source. Selecting OFF stops forwarding and makes the timer publish zero commands; selecting a motion source can immediately re-publish that source's cached last command.
publish_teleop_velocity
Publish one speed and steering-angle command on the teleop multiplexer input. The multiplexer caches it and repeats it at its timer rate only while the teleop source is selected. The receipt confirms transmission to rosbridge, not motion, arrival or stopping.
stop_velocity_source
Set the multiplexer velocity source to OFF, making its timer publish zero speed and steering commands. Input-free, acknowledged service call; no input is accepted during the latch.

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/harunteper__auna
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
1d8bb13d574d
Licence
MIT
Stars
23
Evidence
contract_checked on the fake backend
Backends
fake

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