All capabilities
Robot Fleet Witness Shared-family mapped

Flow Ledger

Flow Conformance Map: Declared Works vs Observed Traffic

Draws a map of where the robots actually drove, and lays it against where the fleet's software says it sent them.

Feasibility path · not a production offer

Fleet Witness Floor Kit

This offer is scoped to this capability only. It does not promote sibling catalog entries or replace physical deployment validation.

~$350 parts · 6 Nodes · ~150 minReview feasibility scope →No charge today · configuration and quote confirmed first
Readiness Shared-family mapped

Mapped to a shared offline runtime family and usable with a recording or compatible ESP32 CSI stream.

Evidence Strong theory Supported hypothesis

Published physics or adjacent results support the hypothesis; capability-specific product and site validation are still required.

Runtime family Zone dwell

Time-in-zone estimate from calibrated presence transitions.

When no ESP32 is connected

No compatible ESP32 stream is connected. Use the bundled Fleet recording; it demonstrates the shared Zone dwell runtime, not independent proof of this capability.

Intended capability

Pilot this intended outcome through the shared Zone dwell family, then validate it against site-specific ground truth: Builds a per-zone, per-shift map of actual fleet traffic — transit counts, transit-interval statistics, busy-fraction — from choke-point CSI links, and lays it against the traffic the fleet manager declares it dispatched. Where the two agree, the map says so with confidence; where they diverge — traffic in a lane no task explains, a declared-busy corridor physics saw quiet — the divergence is recorded as a finding for the certificate stream. The fleet feed is read-only reference, never trusted and never required: with the feed stale, the map degrades to an honest traffic record and says so on its face.

This describes the intended outcome. Readiness is shared-family mapped, evidence is class B, 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.

Shared-family mapped

No rendered revision is available yet.

Bundled recording

A related Fleet scene

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

01 The physics

A link crossing an aisle sees a discrete perturbation event each time a body transits its Fresnel volume; an AMR at 2 m/s crossing a metres-wide zone yields a bounded ~1-2 s window — on the order of ten samples at the measured 6.6 Hz ambient CSI rate. That window supports exactly two honest discriminants: gait-band absence (no 1.5-2.5 Hz cadence energy) and envelope smoothness. A translating AMR writes no sub-Nyquist periodicity, so no constant-period or low-jitter claim is made per transit — the human/machine gate is a statistics verdict with a measured error rate, never an identity. Concurrent transits merge in the superposed channel: the observable is traffic intensity, not a census, and the map is labeled accordingly.

02 Shared processing path

Per-link transit-event segmentation at choke points -> per-transit human/machine gate on the bounded ~1-2 s window (gait-band absence + envelope smoothness on the full-rate CSI path; no periodicity claim) -> per-zone transit counts, interval statistics, busy-fraction -> compartment aggregation across the zone graph -> host-side join against the read-only declared task flow -> divergence scoring per zone-shift cell, filed as findings with confidence.

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-hardware protocol: instrument two choke-point aisles with a scripted AMR running known task manifests plus confederate walkers and cart-pushers; score transit-count accuracy, human/machine gate error, and the cart-pusher confusion rate as a first-class metric alongside divergence detection against the script, over a two-week inventory-churn period to measure baseline decay and set the staleness bound.

04 Commercial hypothesis

'Flow Ledger' — for the intralogistics operations lead who currently grades the fleet on the fleet's own homework: where your robots actually drove, laid against where the fleet manager says it sent them.