INDUSTRIAL ROBOT · CANONICAL DATA MODEL

Franka Emika canonical data model: connect your Franka Emika equipment to any AI agent

2,086 mappings·19 verticals·13 protocols

Forge turns raw Franka Emika tags into one clean, governed schema your AI agent already understands. One MCP call, no per-robot integration project.

Try it free: 3 machines, no credit card → See it work →

Paste your Franka Emika data and see it normalized in 30 seconds. No POC required.

Read-only. Forge reads your Franka Emika data through standard industrial protocols. Read-only. Your equipment is never at risk.

The problem

Why Franka Emika data is hard to integrate

Franka's FCI publishes joint state at 1 kHz over ROS 2 / libfranka as flat arrays. Position, torque and collision state need a schema before any agent can supervise the arm.

Typical Franka Emika equipment communicates over ROS 2 (DDS), HTTP / REST. Each firmware revision, model line and integrator names the same physical quantity differently, so every AI or analytics project pays the integration tax again, the tax that cancels 40% of industrial AI deployments before they ship.

The solution

One universal schema for every Franka Emika robot

Forge resolves Franka Emika telemetry into Forge's canonical field set, the same 985 canonical fields defined, used across 45 vendor packs. Point Forge at the robot, pass oem: "franka", and spindle speed is spindle_speed_rpm whether it came from a Franka Emika controller or anything else on the floor.

ROS 2 (DDS)HTTP / REST

45OEM packs in production

11Canonical industrial robot fields

2,086Mappings in production

Field coverage

What Forge resolves for Franka Emika

Confirmed canonical fields your agent gets from Franka Emika robots, drawn from Forge's 2,086-mapping corpus:

robot.joint.positionrobot.joint.velocityrobot.joint.effortrobot.joint.currentrobot.joint.temperaturerobot.tcp.poserobot.tcp.speedrobot.tcp.forcerobot.payloadrobot.moderobot.safety.status_bits

Sample normalization

Raw tag in		Canonical field out	Meaning
joint_1_deg: 37.4	→	robot.joint.position: 37.4	joint 1 angle
tcp_speed: 250	→	robot.tcp.speed: 250	TCP speed
payload_kg: 7.5	→	robot.payload: 7.5	payload
op_mode: "AUTO"	→	robot.mode: "AUTO"	operating mode

30-second deployment

Add Franka Emika to your agent with one call

No SDK, no per-tag mapping, no historian project. Connect the MCP server and normalize live Franka Emika data:

claude mcp add --transport http forge https://mcp.foundrynet.io/mcp --header 'Authorization: Bearer YOUR_API_KEY'

# normalize raw Franka Emika telemetry into the universal schema

curl -s https://forge.foundrynet.io/v1/normalize \

-H 'Content-Type: application/json' \

-d '{"data": {"joint_1_deg": 37.4, "tcp_speed": 250, "payload_kg": 7.5}, "oem": "franka"}'

{"robot.joint.position": 37.4, "robot.tcp.speed": 250, "robot.payload": 7.5, "coverage": "100%", "confidence": 0.97}

Unknown tags never get force-mapped. Fields below the confidence floor abstain rather than guess, so your agent never acts on a bad reading.

Start free: Forge API, 3 machines → See the full demo →

Where Franka Emika fits

Protocols
ROS 2 (DDS) HTTP / REST

Vertical
industrial robot

Other industrial robot vendors
ABB Robotics KUKA Universal Robots Fanuc Robotics Yaskawa Motoman Doosan Robotics

Same protocols, other industries
MiR (Mobile Industrial Robots) OTTO Motors 6 River Systems AGILOX

Also searched as franka, franka emika, franka_emika, panda, fci