Skip to content
Technology · Stack

AI / ML Stack

Data → Train → Deploy → Audit. Four layers, each constrained by the same three operating principles. We are precise about what ships and what does not.

Four layers.

  1. 01

    Data

    AVIX dataset (Korean airfield species + global migratory profiles) + STANAG 2103 reference scenarios. Doctrine-tagged at ingest so every downstream artefact carries provenance.

    • AVIX dataset · 250K labelled frames
    • CBRN scenario corpus · 40 STANAG-categorised cases
    • Habitat profiles · LULC + species, per coverage cone
  2. 02

    Train

    YOLO-class detection + Re-ID heads trained on edge-friendly backbones (Jetson Orin Nano target). Decision-support layer trained on doctrine-grounded prompt corpora rather than synthetic augmentation.

    • YOLO-class detector · 4 ms/frame target
    • Re-ID tracker · multi-target persistence
    • Doctrine prompt fine-tuning · TPE-001~006
  3. 03

    Deploy

    Edge inference at the runway / vertiport / hazard cell. No GPU clusters in the field — every model has to run on consumer-grade edge hardware to pass deployment.

    • Jetson Orin Nano · 8 GB
    • TensorRT-class quantisation
    • OTA model updates · sandbox-gated
  4. 04

    Audit

    Every entity we publish carries a `_uamkt_extensions:doctrine_ref` tag. Allied operators replay our submissions against their own validation harness before promoting them to operational decision surfaces.

    • Doctrine-ref payload on every entity
    • Replay harness · 19/19 reference run
    • Public sample payloads (Phase 2)
Principles

Three checks.

Each principle is a binary gate: pass or do not ship. The bar is high on purpose — partners who adopt our outputs inherit our gates.

  1. 01

    Edge first

    No model ships if it cannot run on Jetson-class hardware in the field. Cloud inference is a fallback, not a target.

  2. 02

    Doctrine-tagged

    Every output is annotated with the allied doctrine reference it was checked against. Untagged outputs do not reach the catalog.

  3. 03

    Replayable

    Every published entity is reproducible from its source frames + model version. Audits do not stall waiting for vendor support.