Flare Aerospace

Products

TWO FAMILIES. ONE AUTONOMY STACK.

Flare is developing two complementary families: localization and reference extension, and mission intelligence and autonomous execution. Research evidence and intended architecture are distinct.

Family 01 / Localization & Anchor System

HANSEL

LOCALIZE / Research prototype

HANSEL is Flare's localization research stack for turning UAV observations into map-referenced position hypotheses. It extracts semantic road geometry, compares it with public vector maps, evaluates competing poses, and can withhold a fix when the evidence is insufficient.

Research workflow

  1. Sense the environment
  2. Understand semantics
  3. Align with maps
  4. Determine global position

PAIRED WITH GRETEL

Illustration of HANSEL localization research: environment, semantics and map layers inform a map-referenced position hypothesis.ENVIRONMENTSEMANTICSMAP ALIGNMENTGLOBAL POSITION
Research prototype. Illustrative architecture.

Family 01 / Localization & Anchor System

GRETEL

EXTEND / Under development

GRETEL is an in-development reference-extension architecture designed to carry a trusted global position into areas where visual map features alone may be insufficient, using deployable UWB anchors. The architecture connects a HANSEL global reference to a registered local reference for nearby systems; field validation is not established.

Intended workflow

  1. Receive HANSEL's reference
  2. Deploy physical ground anchors
  3. Extend the reference
  4. Support nearby systems

PAIRED WITH HANSEL

Illustration of GRETEL's under-development architecture: a reference connects to ground anchors from left to right. A shared dome depicts intended local coverage, not field validation.TRUSTED REFERENCEGROUND ANCHORSLOCAL POSITIONING AREA
Under development. Illustrative architecture.

Family 02 / Agentic Autonomous UAV System

PROSPERO

DECIDE / In development

PROSPERO is being developed as mission intelligence that turns operator intent into structured mission plans for autonomous aerial systems. The intended workflow covers structured intent, task decomposition, mission planning, and allocation.

Intended workflow

  1. Interpret human intent
  2. Decompose tasks
  3. Plan the mission
  4. Allocate actions

PAIRED WITH ARIEL

Mission input

Search this area and find black vehicles.

Illustration of an in-development mission-planning workflow: human intent becomes area, target and task, then a plan. Observations inform replanning.AREASEARCH REGIONSEARCH ATARGETBLACK VEHICLESDETECTTASKFIND / COUNTSEARCH BSEARCH CREPLANNEDTAKEOFFTRANSITREPORTDECOMPOSEPLAN / ALLOCATE
In development. Illustrative architecture.

Family 02 / Agentic Autonomous UAV System

ARIEL

ACT / Execution architecture

ARIEL is Flare's intended onboard execution layer, designed to turn mission plans into flight, observation, action, and feedback. It is an execution architecture, not a flight-validated product; real flight-controller integration has not been established by the current evidence.

Intended workflow

  1. Receive the mission
  2. Follow the route
  3. Observe and act
  4. Verify and return feedback

PAIRED WITH PROSPERO

Illustration of an intended execution architecture: mission plans connect to flight, observation, feedback and replanning. Not evidence of flight-tested integration.ABCBLACK VEHICLES / 01MISSION COMPLETE
Execution architecture. Illustrative architecture.

Research and technical collaboration inquiries.

Get in touch