TaxiToLearn · Project Milestone 3 · In Progress

The control tower
on your desktop.

ATC simulator with AI-driven virtual pilots. No cloud costs.
Built to democratize aviation training on consumer hardware.

View on GitHub

How It Works

Any airport. Any callsign.

AIrport Ground Control Interface

Load any ICAO airport and start controlling. Each AI agent acts as an independent pilot — listening to your instructions, reasoning over them, and transmitting a readback through synthesised voice in real time. Three standard positions cover the full flight cycle, from engine startup to takeoff and from landing to stand.

DEL

Clearance Delivery — Flight plan clearance.
Example phraseology

CTLR "Iberia 3142, cleared to Palma via LARPA6Q, runway 24L, initial climb 10,000 feet, QNH 1018, squawk 2512."

IB3142 · AI — Agent generated response "Cleared to Palma via LARPA6Q, runway 24L, initial climb 10,000 feet, QNH 1018, squawk 2512, Iberia 3142."

GND

Ground Control — Taxi management.
Example phraseology

CTLR "Iberia 3142, taxi to holding point runway 25L via taxiways Alpha, Bravo."

IB3142 · AI — Agent generated response "Taxi to holding point runway 25L via Alpha, Bravo, Iberia 3142."

TWR

Tower Control — Takeoff and landing authorization, and separation in the traffic circuit.
Example phraseology

CTLR "Iberia 3142, wind 260 degrees, 12 knots, runway 25L, cleared for takeoff."

IB3142 · AI — Agent generated response "Cleared for takeoff runway 25L, Iberia 3142."

Why AIrport

Practice without consequence.

Offline & X-Plane 12

Built specifically for X-Plane 12 simulator. Full offline operation on consumer hardware without internet connectivity required.

Simulation Focused

Designed for realistic ATC training in X-Plane 12. Virtual pilots respond with authentic ICAO phraseology during flight simulation.

No Cloud Required

Everything runs locally on your machine. No API costs, no subscriptions, no external dependencies — just pure offline simulation. If needed, you can optionally pay for API consumption.

Watch aircraft move across the airport in real time — taxiing, lining up, and taking off — all driven by X-Plane 12 integration responding directly to your ATC instructions.

LEST airport in X-Plane 12

LEST airport in X-Plane 12

Tech Stack

Engineering, component by component.

Each piece chosen for a concrete reason: local performance, minimal latency, and zero cloud dependencies.

Core LLM

llm

Ollama

Local LLM inference without cloud, without quotas.

Orchestration

◈

Google ADK

Agent Development Kit for building virtual pilots with memory and persistent state.

Speech Input

asr

Whisper

Offline speech recognition. The controller speaks — Whisper transcribes in real time.

Speech Output

tts

Local TTS

Voice synthesis with aeronautical normalization: numbers, callsigns, and ICAO phraseology.

Infrastructure

🐳

Docker

Isolated microservices. Each subsystem is an independent, restartable container.

Real Time

↯

Redis

Message bus and shared state between microservices. Sub-millisecond latency on local hardware.

Persistence

▤

PostgreSQL

Storage for flights, traffic, and simulation sessions for post-analysis.

Simulator

✈

X-Plane 12

Direct integration via XPPython3 for aircraft spawning at the simulated airport.

Timeline

From idea to demo.

Real project progress, no marketing.

✓

Milestone 1 · Completed

Microservices architecture & persistence

Docker infrastructure, PostgreSQL schema, Redis event bus, and first HMI prototype with electronic flight strips (EFS).

✓

Milestone 2 · Completed

Aircraft spawning in X-Plane

XPPython3 integration for spawning aircraft at any ICAO airport within X-Plane 12.

◎

Milestone 3 · In Progress

Agents configuration & sim deployment

Google ADK orchestration of virtual pilots with memory and full voice pipeline (Whisper → LLM → TTS) deployed in the simulation.

○

Milestone 4 · Planned

X-Plane aircraft movement

Aircraft responding in real time to controller instructions — taxi routing, lineup, takeoff clearance, and landing sequences.

○

Milestone 5 · 2026

Session reporting & public demo

Post-session analysis, performance metrics, and public demo at LEBL (Barcelona-El Prat). Open release of the project.