Browse all documentation

CORE CONCEPTS

Images and sensors

Use images, image views, depth frames, GPS, IMU, BLE, Wi-Fi, or other sensor readings to add visual and device-state context to a spatial request.

Context, not the primary signal

Images and sensor readings supplement geometry; they do not replace it. Rowe answers measurement questions from the structured scene. A photograph helps disambiguate what an object is, not how big it is.

What you can attach

Raster frames, multi-view image sets, depth maps, and device state all ride alongside the scene in the same request, so one call carries both the geometry and whatever observed it. Attach only what the task needs: every field you send counts as input spatial tokens.

  • image / images — single or multiple raster frames
  • image_views — multi-view context for one object
  • sensor_readings — IMU, GPS, altimeter, or other device state

Sending images alone

A request with images and no cad_scene or point_cloud_scene is doing image reasoning, not spatial reasoning. It will return something, but nothing in it is grounded in measured geometry — do not treat those numbers as measurements.

Request fields

The full input contract, shared by every task.

modelstring

Model id. Use rowe-1.0.

input.task_typestring

fit, stability, placement, embed, understand, reconstruct, predict, act, or optimize.

input.cad_sceneobject

Native CAD scene with B-rep solids, drawing entities, dimensions, constraints, and optional feature_tree. Preferred for STEP, IGES, DXF, PDF, SVG, and draw.io workflows.

input.previous_cad_sceneobject

Optional previous native CAD scene for compare and temporal tasks.

input.point_cloud_sceneobject

Current 3D scene with one or more point cloud groups.

input.previous_point_cloud_sceneobject

Optional previous scene for temporal prediction.

input.image / input.imagesobject

Optional raster frames, depth maps, or multi-view visual context.

input.sensor_readingsobject

Optional IMU, GPS, BLE, WiFi, altimeter, or device state readings.

input.goalobject

Optional target state for action, routing, placement, or optimization tasks.

input.object_idstring

Primary object id used by fit, stability, placement, and tracking tasks.

input.secondary_idstring

Target or container object id for fit and placement tasks.

input.detailstring

Use compact to reduce structured prediction detail for small or latency-sensitive requests.