> For the complete documentation index, see [llms.txt](https://docs.konnex.world/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.konnex.world/subnets-workload-classes/drone-navigation.md).

# Drone navigation

**Workload class:** vision–language-driven autonomous flight.

Operators issue **text missions**; miners compete on **navigation and execution policies**; validators score whether the run matches the **task instruction** (safety, task match, geospatial correctness). [Proof-of-Physical-Work (PoPW)](/understand-konnex/contracts-and-popw.md) binds the instruction hash, policy trace, and hardware-attested sensor data.

## Testnet

The public dashboard URL for this workload will be announced with the testnet release.

## Task shape (illustrative)

Users typically send natural-language instructions such as: *"Fly to the red-brick building and photograph the roof."* The exact schema (fees, rewards, attachments) is defined by the live subnet UI and chain integration.

## Why this matters

Aerial data often underwrites insurance, maintenance, and engineering decisions. A self-reported log from the same party that operated the aircraft is not a substitute for independently scored evidence tied to a signed, onchain instruction.

## See also

* [OpenFly & OpenFly-Agent](/supported-ai-models/openfly.md) — aerial VLN / language-driven flight
* [Subnets overview](/subnets-workload-classes/subnets.md)
* [Proof-of-Physical-Work](/understand-konnex/contracts-and-popw.md)