research(R18): disaster response — first vertical integrating with existing repo crate (wifi-densepose-mat) (#737)
Third 'vertical demonstrates loop generality' tick. First vertical to
integrate with an existing repo crate (wifi-densepose-mat), making
loop-to-production path most direct.
Headline: rubble is RF-leaky, not RF-opaque
- Steel (1mm): 2,674 dB (opaque)
- Mixed rubble 1-2m: 40-80 dB
- Brick 10cm: 8-12 dB
- Concrete 10cm: 20-30 dB
- Drywall 1.5cm: 1-2 dB
ESP32-S3 121 dB link budget gives 40-80 dB margin through typical
rubble. Survivors at 1m depth: +37 dB (feasible), 2m: +7 dB (marginal),
3m: infeasible. Dramatically better than R11 maritime through-bulkhead
case.
Loop primitives -> MAT crate enhancements:
- R12.1 pose-PABS: 9.36x fewer false alarms
- R6.2.5: multi-survivor union (bounded ~4)
- R1 CRLB: ~25 cm position precision
- R14 V1 + R15: rate-level vitals confirmation
- R3 + AETHER: survivor-vs-rescuer disambiguation
- R7 mincut: BINDING at disaster sites
- ADR-109 Dilithium: audit trail integrity
Six-cog roadmap:
- cog-mat-survivor-detect (NOW): wifi-densepose-mat baseline
- cog-mat-pose-pabs (5y): + R12.1
- cog-mat-multi-survivor (5y): + R6.2.5
- cog-mat-vitals-confirm (5y): + R14 V1 + R15
- cog-mat-survivor-vs-rescuer (10y): + R3 + library
- cog-mat-cross-deploy-fed (15y): + ADR-105-108 consent-bounded
Three deployment scenarios:
- Rapid response 5y: 00/survey unit, FEMA model
- Pre-staged at seismic sites 10y: auto-activate on tremor
- Cross-disaster fed 15y: consent-bounded across sites
Vertical comparison (5 verticals now):
- R18 disaster: rubble 40-80 dB, trapped, R7 binding, existing crate
- R16 healthcare: air, stationary patients, R7 nice-to-have
- R17 industrial: air, mobile workers, R7 binding
Three of three target verticals (clinical/industrial/disaster) work
with same architecture. Strong evidence loop is vertical-agnostic.
Honest scope:
- No bench-validated disaster-site data (ethics: can't simulate)
- R7 mincut hostile-RF requirement
- Cross-disaster fed has consent questions
- Time-pressure tuning aggressive toward false-positive
- MAT crate API doesn't yet consume R6.1 multi-scatterer
- Steel-rubble (basement w/ rebar) impossible per R11
- Underwater impossible per R11 saltwater
Composes with every loop thread (R1, R6/R6.1, R6.2.2/.5, R7, R10, R11,
R12/R12.1, R13 NEG, R14, R15, R3) + all ADRs (105-109, 113) + R16/R17
parallel patterns.
R18 special status: FIRST VERTICAL to integrate with existing repo
crate. Loop-to-production path is shortest because production code
exists; loop primitives enhance rather than replace.
Coordination: ticks/tick-34.md, no PROGRESS.md edit.
Loop now has 6 exotic verticals:
1. R10 wildlife
2. R11 maritime
3. R14 empathic appliances (home)
4. R16 healthcare
5. R17 industrial
6. R18 disaster (first to integrate with existing crate)
472774d3f8