ruv
|
d4dc5cb0bc
|
Merge remote-tracking branch 'origin/claude/use-cases-implementation-plan-tT4s9' into ruvsense-full-implementation
|
2026-03-01 21:21:24 -05:00 |
|
Claude
|
374b0fdcef
|
docs: add RuView (ADR-028) sensing-first RF mode for multistatic fidelity
Introduce Project RuView — RuVector Viewpoint-Integrated Enhancement — a
sensing-first RF mode that improves WiFi DensePose fidelity through
cross-viewpoint embedding fusion on commodity ESP32 hardware.
Research document (docs/research/ruview-multistatic-fidelity-sota-2026.md):
- SOTA analysis of three fidelity levers: bandwidth, carrier frequency, viewpoints
- Multistatic array theory with virtual aperture and TDM sensing protocol
- ESP32 multistatic path ($84 BOM) and Cognitum v1 + RF front end path
- IEEE 802.11bf alignment and forward-compatibility mapping
- RuVector pipeline: all 5 crates mapped to cross-viewpoint operations
- Three-metric acceptance suite: joint error (PCK/OKS), multi-person
separation (MOTA), vital sign sensitivity with Bronze/Silver/Gold tiers
ADR-028 (docs/adr/ADR-028-ruview-sensing-first-rf-mode.md):
- DDD bounded context: ViewpointFusion with MultistaticArray aggregate,
ViewpointEmbedding entity, GeometricDiversityIndex value object
- Cross-viewpoint attention fusion via ruvector-attention with geometric bias
- TDM sensing protocol: 6 nodes, 119 Hz aggregate, 20 Hz per viewpoint
- Coherence-gated environment updates for multi-day stability
- File-level implementation plan across 4 phases (8 new source files)
- ADR interaction map: ADR-012, 014, 016/017, 021, 024, 027
https://claude.ai/code/session_01JBad1xig7AbGdbNiYJALZc
|
2026-03-02 02:07:31 +00:00 |
|
Claude
|
c707b636bd
|
docs: add RuvSense persistent field model, exotic tiers, and appliance categories
Expands the RuvSense architecture from pose estimation to spatial
intelligence platform with persistent electromagnetic world model.
Research (Part II added):
- 7 exotic capability tiers: field normal modes, RF tomography,
intention lead signals, longitudinal biomechanics drift,
cross-room continuity, invisible interaction layer, adversarial detection
- Signals-not-diagnoses framework with 3 monitoring levels
- 5 appliance product categories: Invisible Guardian, Spatial Digital Twin,
Collective Behavior Engine, RF Interaction Surface, Pre-Incident Drift Monitor
- Regulatory classification (consumer wellness → clinical decision support)
- Extended acceptance tests: 7-day autonomous, 30-day appliance validation
ADR-030 (new):
- Persistent field model architecture with room eigenstructure
- Longitudinal drift detection via Welford statistics + HNSW memory
- All 5 ruvector crates mapped across 7 exotic tiers
- GOAP implementation priority: field modes → drift → tomography → intent
- Invisible Guardian recommended as first hardware SKU vertical
DDD model (extended):
- 3 new bounded contexts: Field Model, Longitudinal Monitoring, Spatial Identity
- Full aggregate roots, value objects, domain events for each context
- Extended context map showing all 6 bounded contexts
- Repository interfaces for field baselines, personal baselines, transitions
- Invariants enforcing signals-not-diagnoses boundary
https://claude.ai/code/session_01QTX772SDsGVSPnaphoNgNY
|
2026-03-02 01:59:21 +00:00 |
|
Claude
|
25b005a0d6
|
docs: add RuvSense sensing-first RF mode architecture
Research, ADR, and DDD specification for multistatic WiFi DensePose
with coherence-gated tracking and complete ruvector integration.
- docs/research/ruvsense-multistatic-fidelity-architecture.md:
SOTA research covering bandwidth/frequency/viewpoint fidelity levers,
ESP32 multistatic mesh design, coherence gating, AETHER embedding
integration, and full ruvector crate mapping
- docs/adr/ADR-029-ruvsense-multistatic-sensing-mode.md:
Architecture decision for sensing-first RF mode on existing ESP32
silicon. GOAP integration plan (9 actions, 4 phases, 36 cost units).
TDMA schedule for 20 Hz update rate from 4-node mesh.
IEEE 802.11bf forward-compatible design.
- docs/ddd/ruvsense-domain-model.md:
Domain-Driven Design with 3 bounded contexts (Multistatic Sensing,
Coherence, Pose Tracking), aggregate roots, domain events, context
map, anti-corruption layers, and repository interfaces.
Acceptance test: 2 people, 20 Hz, 10 min stable tracks, zero ID swaps,
<30mm torso keypoint jitter.
https://claude.ai/code/session_01QTX772SDsGVSPnaphoNgNY
|
2026-03-02 00:17:30 +00:00 |
|
Claude
|
91a3bdd88a
|
docs: Add remote vital sign sensing modalities research (RF, radar, quantum)
Covers Wi-Fi CSI, mmWave/UWB radar, through-wall RF, rPPG, quantum radar,
and quantum biomedical instrumentation with cross-modality relevance to
WiFi-DensePose ADR-014 algorithms.
https://claude.ai/code/session_01Ki7pvEZtJDvqJkmyn6B714
|
2026-02-28 14:40:00 +00:00 |
|
Claude
|
cc82362c36
|
docs: Add SOTA research on WiFi sensing + RuVector with 20-year projection
Comprehensive research document covering:
- WiFi CSI pose estimation SOTA (CVPR 2024, ECCV 2024, IEEE IoT 2025)
- ESP32 sensing benchmarks (88-97% accuracy, 18.5m through-wall)
- HNSW vector search for signal fingerprinting
- ONNX Runtime WASM for edge inference
- NIST post-quantum cryptography (ML-DSA, SLH-DSA) for sensor mesh
- WiFi 7/8 evolution (320MHz channels, 3984 CSI tones, 16x16 MIMO)
- 20-year projection through 2046 with cited sources
https://claude.ai/code/session_01Ki7pvEZtJDvqJkmyn6B714
|
2026-02-28 09:12:02 +00:00 |
|