All capabilities
Hospitality & Retail Research concept

StockSense

ShelfPulse — stockout and planogram-change detection

Knows when a shelf is swept empty in seconds.

Readiness Research concept

A frontier proposal with a validation plan, not an implemented detector.

Evidence Frontier Unvalidated concept

An early research proposal with no capability-specific product validation yet.

Runtime family Not mapped

No browser runtime is assigned to this capability yet.

Why live sensing is unavailable

This is a research concept, not an implemented detector. Show its physics and validation plan without generating synthetic claims.

Intended capability

Research whether the field could support this proposed outcome: Detects when a high-value shelf section is emptied, restocked, or physically rearranged — including sweep-theft events where a whole facing vanishes in seconds.

This describes the intended outcome. Readiness is research concept, evidence is class C, 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.

Research concept

No rendered revision is available yet.

Bundled recording

A related Hospitality scene

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

01 The physics

Densely packed product mass (liquids, foils, metal cans) is a strong dielectric/conductive scatterer; removing it opens new propagation paths and removes reflections, shifting specific CIR tap delays and the local sigma/eps_r map. A shelf-sweep is a step change; normal shopping is a slow ramp.

02 Shared processing path

CIR sparse recovery referenced to overnight baseline -> RFF/NeRF differential sigma/eps_r map per shelf voxel -> CUSUM step detector for sweeps vs Kalman ramp tracking for depletion; axis discovery calibrates each shelf by deliberately emptying it once.

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

Own experiment: instrumented gondola with liquor/detergent (high-dielectric SKUs), scripted removal patterns, blind detection of step vs ramp; no public dataset covers this.

04 Commercial hypothesis

Camera-free stockout and sweep-theft alarm for the store manager: know within a minute that the razor-blade shelf just got emptied.