Frontier — the Field Lab Shared-family mapped

Baselines you can cite

Certified-Quiescence Baseline Gate

Before the system learns what an empty room looks like, it makes sure the room really is empty — even of someone sitting perfectly still.

Open demo room Design this solution See how it works

Readiness Shared-family mapped

Mapped to a shared offline runtime family and usable with a recording or compatible ESP32 CSI stream.

Evidence Supported hypothesis

Published physics or adjacent results support the hypothesis; capability-specific product and site validation are still required.

Runtime family Presence

Calibrated motion and presence score from CSI variance and change statistics.

When no ESP32 is connected

No compatible ESP32 stream is connected. Use the bundled Frontier recording; it demonstrates the shared Presence runtime, not independent proof of this capability.

Intended capability

Pilot this intended outcome through the shared Presence family, then validate it against site-specific ground truth: A platform-wide integrator gate: slow-drift capabilities (moisture tomography, cure tracking, overnight scene-change, taught axes) accept new baseline data only during windows a room's radar certifies as human-empty — killing the stationary-occupant confounder that silently poisons quiet-window learning.

This describes the intended outcome. Readiness is shared-family mapped, evidence is class B, and a catalog mapping or recording is not proof of this outcome at a real site.

Solution blueprint

See the environment before installing it.

This exact kit is one of 191 first-class designs. It includes geometry, objects, nodes, wording, scenarios, installation, limitations, and catalog-bound readiness.

Shared-family mapped

No rendered revision is available yet.

Bundled recording

A related Frontier scene

This is one recorded vertical scenario. It is not separate validation of every capability in the catalog.

01 The physics

The contamination CSI cannot self-detect is a person who is present but still; LD2410C static micro-motion detection holds exactly that occupant to 4-6 m in-cone. Requiring moving AND static energy at noise floor across the certified cones for the whole accumulation window makes 'empty' an AND across two independent modalities instead of an inference from one.

02 Shared processing path

Baseline-window request -> LD2410 moving+static noise-floor attest across certified cones for the full window -> CSI quiet cross-check -> baseline accepted with quiescence certificate | any energy -> window discarded, never averaged

This is a capability design path. Components may be shared with other catalog entries; it is not presented as a unique algorithm.

03 Validation plan

Poisoning trials: seed still occupants during scheduled baseline windows and measure contamination with and without the gate across two slow-drift capabilities; certificate-scope audit confirming uncovered zones are marked uncertified.

04 Commercial hypothesis

'Baselines you can cite' — for integrators whose slow-drift instruments must prove the room was empty when they learned it.