sjtu_drone Gazebo quadrotor simulation — device market

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/novog93__sjtu_drone

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/novog93__sjtu_drone --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": {
    "sjtu-drone": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "robots/novog93__sjtu_drone",
        "--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_last_cmd_vel
read_state
read_pose
read_mode

Adjusts

Nothing declared.

Actions

takeoff: Publish one std_msgs/Empty on /simple_drone/takeoff. The callback only moves the state machine from LANDED_MODEL to TAKINGOFF_MODEL; the receipt proves the publication, not that the simulated drone left the ground.
land: Publish one std_msgs/Empty on /simple_drone/land. The callback only moves the state machine to LANDING_MODEL; the receipt proves the publication, not that the simulated drone landed.
reset: Publish one std_msgs/Empty on /simple_drone/reset. The plugin's callback resets the attitude and velocity PID controllers and the current force and torque but keeps the flight state and stored cmd_vel; it is not an acknowledged stop or an operator safety reset.
publish_cmd_vel: Publish one geometry_msgs/Twist on /simple_drone/cmd_vel. The fields are position targets in position-control mode and velocity/tilt/rate otherwise; the receipt is a publication acknowledgement only.
set_position_control: Publish one std_msgs/Bool on /simple_drone/posctrl. The callback only stores the flag; the receipt proves the publication, not the resulting control mode.
set_velocity_mode: Publish one std_msgs/Bool on /simple_drone/dronevel_mode. The callback stores the flag and publishes the resulting cmd_mode String; the receipt proves the publication only.
reset_world: Call the /reset_world std_srvs/Empty service (gazebo_ros) that the clone's reset_sim.sh uses. It resets the simulated world, but the plugin keeps its flight state and stored cmd_vel, so a flying drone keeps flying; it is not a stop.

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/novog93__sjtu_drone
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

Upstream: novog93/sjtu_drone
Pinned commit: 3f8627ebddf3
Licence: GPL-3.0
Stars: 211
Evidence: contract_checked on the fake backend
Backends: fake

The driver package MHS/drivers/robots/novog93__sjtu_drone wraps the upstream code at the pinned commit. Its REFERENCE.md documents the full contract: every value, action, unit, limit and the safety declaration.