aerostack

Search Aerostack

Norwegian

Rydoo Accounts Payable AI invoice automation at Norwegian

MidAmerica St. Louis

GoodMaps indoor navigation at MidAmerica St. Louis Airport

Lyon Saint-Exupéry Airport

Stan robotic valet parking at Lyon Saint-Exupéry

London Heathrow

Facial-recognition eGates at Heathrow

Almaty International Airport

Q-Gate biometric passport-control terminals at Almaty

Pittsburgh International Airport

Arrow Analytics EZ-Board computer-vision carry-on analytics test at PIT Gate A7

Federal Aviation Administration

FAA SMART airspace and trajectory management platform

Dubai International

Dubai Police AI systems for passenger screening, unattended baggage and camera analysis at Dubai airports

Airport intelligence / Munich

Munich: a wheelchair located, a turnaround programme promised

Munich's camera-based wheelchair tracking addresses a small but immediate passenger-assistance problem. Its planned Assaia rollout covers a larger operational ambition, but the 150 stands announced are not a verified live installation.

Aerial view of Terminal 1 at Munich Airport, January 2017
Aerial view of Terminal 1 at Munich Airport, January 2017. Photograph: Vasyatka1 / CC BY-SA 4.0 (cropped to fit). Shows the airport, not an AI implementation.
The picture at Munich

A practical problem in plain sight

Airport teams can struggle to say where an available wheelchair is at the moment a passenger needs one. Munich is using image analysis from existing cameras to show availability, an unusually specific application of computer vision.

A very different programme was announced for aircraft turnaround monitoring across 150 stands, using Assaia's ApronAI. The source describes a supplier selection rather than completed installation; treating those stands as live would overstate the position.

The airport has also modernised security scanning and contracted controller workstation technology. Neither announcement supplies evidence that an AI capability is already operational in those systems.

Selected implementations

An immediate operational use and a larger commitment

01 / Deployed · limited scope

Finding the wheelchair that is already there

The operational problem

A passenger-assistance team needs to know which wheelchairs are available without sending staff to search for them.

What the sources report

Reply describes Munich using its Vision Detection Agent to recognise and locate wheelchairs from camera feeds. The company calls the wheelchair application a proof of concept and describes possible future extensions separately.

Why it matters

A live location signal can shorten the search for equipment if staff rely on it and recognition accuracy is adequate.

What remains unproven

No independently verified accuracy, utilisation or passenger-assistance waiting-time result is available.

Sources and verification (1)

Reply case study · Evidence grade B

Evidence supports a reported claim; it does not automatically establish a measured operating benefit.

02 / Contracted

The 150-stand turnaround ambition

The operational problem

A large apron operation needs a shared view of stand events and exceptions.

What the sources report

Assaia announced in August 2025 that Munich had selected ApronAI to monitor 150 stands initially, with further expansion envisaged.

Why it matters

The proposed scale would make common data and operational response across stands particularly important.

What remains unproven

No confirmed go-live date, installed stand count or measured punctuality result is established.

Sources and verification (1)

Assaia · Evidence grade B

Evidence supports a reported claim; it does not automatically establish a measured operating benefit.

The wider register

What else is happening at Munich?

CT security lanes in Terminal 2 are proven equipment upgrades but not described as AI. The contracted OneControl working positions similarly include no specified operational AI function in the supplier's announcement.

CT security lanes in Munich Airport Terminal 2 · Deployed · full scale

Munich Airport opened 15 modernised central security lanes with CT scanners in Terminal 2 on 7 April 2025, the airport said.

Sources and verification (1)

Munich Airport · Evidence grade A

Evidence supports a reported claim; it does not automatically establish a measured operating benefit.

Open the full record →

ADB SAFEGATE OneControl controller working position contract at Munich Airport · Contracted

Munich Airport has awarded ADB SAFEGATE a multi-phase contract for a next-generation Integrated Controller Working Position based on the company's OneControl software, ADB SAFEGATE announced on 19 December 2024. The work is tied to the objectives of Common Project 1 in the European ATM Master Plan.

The release lists ground movement optimisation, artificial intelligence and ADB SAFEGATE's Airside 4.0 programme as drivers of Munich's operational performance. It does not describe any AI function in the controller working position itself.

Alexander Hoffmann of Munich Airport's operations management is quoted describing the contract as a significant investment. No go-live date or delivery phase has been published, and until one of the companies describes a specific AI feature, this record is an apron control modernisation contract.

Sources and verification (1)

ADB SAFEGATE · Evidence grade B

Evidence supports a reported claim; it does not automatically establish a measured operating benefit.

Small proof and large promise

Munich's wheelchair tracking is a narrow, tangible problem. The apron project is an ambitious procurement with a bigger potential footprint.

The most useful updates will distinguish proof-of-concept performance from a rollout that has actually entered service.

Live data from the Aerostack register. Status reflects published evidence only. See Our approach for how records are graded.

Aerostack tracks AI deployments across airports and airlines, with the published evidence behind each record. Photography is real aviation imagery. Record thumbnails may show the named airport or airline; other photographs do not.