The evidence is proven or strong, but this capability still needs a capability-specific ESP32 or Rust runtime adapter.
Intended capability
Validate this target only after a capability-specific adapter and ground-truth study exist: Classifies driveway arrivals — car, pedestrian, delivery walk-up — before the door, from indoor nodes: vehicle vs person vs unknown, with approach direction.
This describes the intended outcome. Readiness is needs edge adapter, 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.
No rendered revision is available yet.
Bundled recording
A related Home scene
This is one recorded vertical scenario. It is not separate validation of every capability in the catalog.
01 The physics
A vehicle is a rigid body: narrowband monotone Doppler with smooth deceleration and large RCS through the facade; a walking person carries the 1-3Hz limb-comb signature at low speed; direction falls out of which links perturb in which order.
02 Shared processing path
Edge Doppler summary on facade-adjacent links -> track segmentation -> rigid-line vs gait-comb band classifier + velocity profile -> arrival event with class and direction into the same event stream the perimeter entries use.
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 at three homes, 2 weeks of labeled arrivals (resident cars, deliveries, walk-ups); report class confusion and range at which classification stabilizes.
04 Commercial hypothesis
For the household: 'Know it's a car pulling in, not someone walking up — before the knock.'