Robots · Robot arms and grippers

Panda active-inference simulation

Panda active-inference simulation, adapted from cpezzato/panda_simulation. It reads read_joint_state and read_free_energy; runs set_joint1_effort, set_joint2_effort, set_joint3_effort, set_joint4_effort and 3 more. set_joint1_effort: publish one effort command for panda_joint1 on /robot1/panda_joint1_controller/command; the AIC node may overwrite it, and while the world is paused no effort reaches the joint. A simulator: the market serves it with a stand-in that needs no simulator install.

simulatedRisk R2Apache-2.0contract_checkedserved on the fake backend
openai4s lab add robots/cpezzato__panda_simulation

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/cpezzato__panda_simulation

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/cpezzato__panda_simulation --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": {
    "panda-simulation": {
      "command": "python3",
      "args": [
        "-m",
        "mhs",
        "serve",
        "robots/cpezzato__panda_simulation",
        "--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_joint_state
  • read_free_energy

Adjusts

Nothing declared.

Actions

set_joint1_effort
Publish one effort command for panda_joint1 on /robot1/panda_joint1_controller/command; the AIC node may overwrite it, and while the world is paused no effort reaches the joint
set_joint2_effort
Publish one effort command for panda_joint2 on /robot1/panda_joint2_controller/command; the AIC node may overwrite it, and while the world is paused no effort reaches the joint
set_joint3_effort
Publish one effort command for panda_joint3 on /robot1/panda_joint3_controller/command; the AIC node may overwrite it, and while the world is paused no effort reaches the joint
set_joint4_effort
Publish one effort command for panda_joint4 on /robot1/panda_joint4_controller/command; the AIC node may overwrite it, and while the world is paused no effort reaches the joint
set_joint5_effort
Publish one effort command for panda_joint5 on /robot1/panda_joint5_controller/command; the AIC node may overwrite it, and while the world is paused no effort reaches the joint
set_joint6_effort
Publish one effort command for panda_joint6 on /robot1/panda_joint6_controller/command; the AIC node may overwrite it, and while the world is paused no effort reaches the joint
set_joint7_effort
Publish one effort command for panda_joint7 on /robot1/panda_joint7_controller/command; the AIC node may overwrite it, and while the world is paused no effort reaches the joint

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/cpezzato__panda_simulation
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
58e1675a372b
Licence
Apache-2.0
Stars
78
Evidence
contract_checked on the fake backend
Backends
fake

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