Your fleet and your unit
yoursFinished targets in real time — to the crew and into your command system.
An onboard layer where your AI models run on every frame at full resolution, and a server layer that holds that across the whole fleet. We supply the layer between your hardware and your models — and nothing else changes.
Airframe, payload, sensors, radios, autopilot: untouched. Your models, your data, your archive, your customer relationship. We do not resell computers, we do not replace your models, and we obtain no access to your data.
Finished targets in real time — to the crew and into your command system.
Registry of aircraft and model versions · distribution with staged rollout and rollback · event store · retraining.
Decode · inference of your model on every frame · track · sensor fusion · event · recording · secured perimeter.
Airframe · payload · sensors · communications · autopilot.
Two layers of one system · neither works alone · licensed per platform
Frame rate, range and latency are fixed by the hardware chosen before the first sortie. The only open question is whether that choice can wait. Machine vision on NVIDIA Jetson modules has been recovered from several classes of enemy munition.
A modernised Shahed-136 with a camera and AI-based guidance; an NVIDIA chip among the components.
Defence Intelligence of Ukraine · War&Sanctions portal
A Jetson Orin operating as the terminal guidance system — in effect, a seeker head.
Debris analysis, 2025–2026
A Jetson Orin and a camera previously identified in the jet-powered 'Geran-4'.
Defence Intelligence of Ukraine
Jetson Orin recovered from the debris of drones used in trials of independent target selection on the Zaporizhzhia axis.
The New York Times, August 2026
Within a chosen board the result is decided by three quantities, and only three: how often the aircraft looks, how far away there is anything to see, and how long it takes to say so.
vs 16.7 m at 5 fps
Where the track holds a target through a manoeuvre. No model compensates for the gap between frames.
vs 917 m once the frame is downscaled to a 640 input
Range is geometry — pixels on the target, not TOPS.
vs 794 ms at 7 fps
Routed through the ground, the radio link alone adds ~200 ms — a link the aircraft does not need.
enters the sensor's field of view
full resolution, hardware decode
your model, on every frame
held through the manoeuvre and after loss
three frames of five, not one trigger
on board, with nothing asked of the outside
No link in that chain passes through the radio channel, the ground, or satellite navigation. That the chain closes on the aircraft is the condition for working under jamming — not an extra feature switched on separately.
A neutral layer on top of your computer and your models barely exists on the market.
| Comparison | Vertically integrated system | Build it yourself | Asterioniq |
|---|---|---|---|
| Onboard computer | Theirs | Yours | Your choice, from 22 qualified modules |
| AI models | Theirs | Yours | Yours — we help build and prove them if you want |
| Flight controller & radios | Replaced by theirs | Unchanged | Unchanged |
| Mission coverage | Mostly the terminal phase | Whatever you build | Reconnaissance through terminal guidance |
| Where the data stays | Under their rules | With you | Inside your perimeter, no access for us |
| Time to first deployment | Weeks | About two years | Weeks |
| Who keeps the layer alive | The vendor | Your team, permanently | Us, over the air to the whole fleet |
| What it costs you | You stop being the platform | ~15 engineers, ~$2.03m, ~2 years | From $281.04 per platform per year |