Home · Strong theory
Resident-vs-Stranger Gait Fingerprint
It learns how your family walks — and notices a stranger's steps.
The physics is solid; our own validation is scheduled.
How it works
Everyone's walk stirs the signal with its own rhythm — the sway of the body, the swing of the limbs. Within days the system learns each household member's rhythm. A walk it does not recognize raises a quiet flag; pets and robot vacuums look completely different and never confuse it.
In the physics: Walking produces a micro-Doppler signature: torso oscillation ~1-2 Hz plus limb harmonics up to ~10 Hz, whose cadence, stride-induced Doppler spread, and duty cycle are biometric-grade individual traits (established in WiFi gait-ID literature). Pets and robots occupy distinct micro-Doppler regions — machine-vs-human discrimination is already proven in LF2.
See it work
This is real pipeline output for Home, replayed. The exact reading depends on your room.
Go deeper
How the field becomes an answer
How we prove it
SenseFi and CSI-Bench identity/HAR benchmarks for feature validity; own-hardware enrollment trial with 5 households x 4 people x 2 weeks, report stranger-detection AUC and per-resident confusion.
Who it is for
"Your house knows the difference between your teenager sneaking a snack and a stranger — and only wakes you for the stranger." For premium smart-alarm subscribers.
runtime Runs today in LatentField 2.0 as gait_signature
The matching solution
Complete first-room estimateHome Presence & Intrusion2 nodes · ~$90 parts · 45 min Request kit, subscribe, or set up →Compatible DIY hardware options
45 min · intermediate
60 min · intermediate