Deliveries withnobody at the controls.

Eight drones, four pairs, no dispatcher. Place an order over a real Riyadh neighbourhood and watch the swarm bid for it, fly it, map the streets as it goes, and cover for a drone that falls — live, in 3D, in your browser.

Pairsone carries · one watches the blind side
Real streetsAl Wurud, Riyadh, from OpenStreetMap
Peer-reviewedAlexandria Engineering Journal, 2024
A delivery drone carrying a parcel over rooftops in Al Wurud, its sensor rays sweeping aheadA frame from the simulator — golden hour over Al Wurud
0
drones in four pairs — one carries the parcel, its partner flies behind and above to cover what it cannot see
0
dispatchers — an order is broadcast, the idle pairs bid, and every drone works out the winner for itself
0
real building footprints of Al Wurud, Riyadh, with its real street names — click any roof to deliver there
0
trained weights of the paper's TD3 actor, running in your browser on the depth camera of the drone you follow

From an order to a roof

The paper's delivery flow, running
The appOrderaddress · payloadStep 1Markera unique ArUco codeStep 2Bididle pairs · no dispatcherStep 3Flycarrier + wingmanStep 4Findlower · match the markerStep 5Landrelease on the markerThe logDeliveredor returned, and whyFig. 2 of the paper — as a running systemno marker on the roof? the drone asks, waits, and goes home
The recipient

Orders in an app, gets a unique ArUco marker, and puts it on a flat spot — a roof, a balcony. The marker is the address and the signature: the drone lands on it, and only on it.

The packer

Packs to the airframe's limits and tags the parcel with the same marker. From there nobody touches a control: no pilot, no dispatcher, no route desk.

When it goes wrong

No marker in sight? The drone asks the recipient and hovers on a timer, then returns and logs why. A drone down? It raises the alarm itself and the others decide who takes over.

A swarm that runs itself

Decentralised, by construction

There is no server deciding who flies. Each drone keeps its own table of the others, built from the check-ins it hears over the cell network: where they are, what they hold, how much battery they have left. Select a drone in the simulator and you see the swarm as that drone knows it — and how the picture goes stale when messages stop arriving.

Take every tower down and the drones fall back to passing messages among themselves, hop by hop. Fail a carrier in mid-air and watch the idle pairs bid to recover its parcel.

Group check-in

Every few seconds each drone tells the others its state, position and charge. Nobody collects these; everybody keeps their own copy.

The handshake

Before a mission the carrier and its wingman establish a link: establish, respond, confirm, exchange goals. No reply in time and it is sent again.

Delivery screening

While the carrier is down on the roof, the wingman circles the address and reports the pad clear.

Fall alert

A failing drone broadcasts where it is going down and what it was holding. The takeover is an auction among its peers, not an order from above.

Inside the simulator

Open it →

Four ways to not hit things

And a framework that picks

A map only knows footprints. Lamp posts, power lines, palms, tower cranes, a minaret, a flock of birds — a drone has to see those for itself. The paper's answer is not one avoidance algorithm but a framework that switches between four, depending on what the drone is looking at.

The default is a TD3 agent trained with prioritised replay: a small network that turns a depth image into a velocity. In the simulator that network is the real one, from the project's training runs, and the Algorithms tab shows its output as it flies.

Table 4 of the paperDelivery accuracyEfficiencyCollision avoidance
Proximity avoidance0.950.880.92
Dynamic path planning0.920.850.89
Visual-SLAM integration0.960.910.94
The framework0.970.930.95

The training runs, as logged

Six agents · 14,141 episodes · AirSim

Drawn from the project's own training logs, smoothed with a moving average. Each episode is one attempt to fly a 57-metre street without touching anything. RA2C and R-DQN never reach the end of it. Over its last 300 episodes TD3 with prioritised replay finishes 42 % of the time — the best of the agents whose logs record outcomes — which is why it is the default. PPO's log keeps distances only.

Payload

20 kg

Range

200 km

Top speed

100 km/h

Battery

25,000 mAh

Fuel tank

10 litres

The airframe of the paper's design section: a quad in X configuration with a hybrid power source, a protective dome over the flight computer, and two manipulator arms for the parcel. The drones in the simulator are built to it.

The research behind it

DecentraliDrones began as a research project and became a peer-reviewed paper: a delivery system in which drones fly in pairs, land on ArUco markers, map with visual SLAM, share their waypoints, and hold the swarm together through check-ins rather than a control room. It was trained and flown in Unreal Engine with AirSim.

This web version keeps the system and swaps the workstation for a browser: the neighbourhood is a real one, the swarm's protocol runs message by message, and the trained actor flies on a depth camera rendered on your own graphics card.

Publication

DecentraliDrone: A decentralized, fully autonomous drone delivery system for reliable, efficient transport of goods
Alexandria Engineering Journal 88 (2024) 1–30. Open access (CC BY-NC-ND 4.0).

doi.org/10.1016/j.aej.2023.12.049 ↗

Pricing

DecentraliDrones for your fleet

Contact for pricing →

The simulator is free to fly. For a logistics operator, a hospital group, a campus or a compound we build the real thing around your district: your map, your airframes, your airspace rules — first as a digital twin you can test against, then in the air.

Your ordersYour appor ours, in your nameYour yardYour fleetairframes you chooseYour airspaceYour rulesno-fly · corridors · hoursYour peopleOversightwatch, never steerRecordsYour logsevery flight, every messageone district, end to endpharmacies · campuses · compounds · islands
01Your districtA digital twin of where you actually deliver — streets, roofs, no-fly zones, towers — to plan yards and test routes before anything flies.
02Your airframesThe swarm logic is not tied to one drone. Payload, range and sensors are parameters; pairs can be mixed.
03Your rulesCorridors, altitudes, curfews and the authority's airspace restrictions, enforced by every drone on its own.
04Your appOrdering, marker issue and delivery proof inside your own product, or a white-label one.
05OversightA console like the simulator's for your operations team: watch everything, steer nothing.
06SupportedSet-up, training, regulatory groundwork, and a person to call.
No price list — every deployment is sized on a callContact for pricing →

Place an order

Pick a roof in Al Wurud. The swarm does the rest — and you can ride along, read its messages, or knock a drone out of the sky and see who picks up the parcel.