Automotive · Strong theory

Ghost Passenger — Child/Pet Presence Detection

Knows a sleeping baby or pet is still in the parked car.

Strong theory Strong theory live in runtime

The physics is solid; our own validation is scheduled.

In a parked, locked car, nothing moves — the signal is frozen. A sleeping infant's breathing moves the chest a few millimeters, and that tiny rhythm stands out clearly against total stillness. It works in footwells and under blankets, where cameras and weight mats fail.

In the physics: Respiration displaces the chest ~5mm at 0.1-0.5Hz, modulating CSI phase on cabin multipath; heartbeat proxy at 0.8-2Hz adds a secondary band. In a static parked cabin the RF channel is otherwise frozen, so even sub-mm periodic motion produces a strong SNR deviation from the empty-cabin baseline.
Preparing the recorded fieldLoading real LatentField pipeline output…

This is real pipeline output for Automotive, replayed. The exact reading depends on your room.

Bring this into the real roomCabin Presence Node1 sensing nodes · ~$40 parts · about 45 min
Go deeper

How the field becomes an answer

Micro-Doppler band-pass 0.1-2Hz adaptive PCA + MVE anomaly vs rolling empty-cabin manifold RTI differential to localize which seat/footwell zone.

How we prove it

Own-hardware: 2-3 ESP32 nodes in a parked car, N=10 subjects + infant mannequin with breathing simulator, blanket/footwell occlusion matrix; cross-check breathing extraction against OPERAnet respiration ground truth.

Who it is for

Euro NCAP 2025 Child Presence Detection compliance at $30/car using the WiFi chipset already in the head unit — sold to Tier-1 ADAS product managers and OEM safety leads.

runtime Runs today in LatentField 2.0 as occupancy_estimate

Complete first-room estimateCabin Presence Node1 nodes · ~$40 parts · 45 min Request kit, subscribe, or set up →
Compatible DIY hardware options
Prosumer DIY$18–35

45 min · intermediate

← All Automotive capabilities