docs: make K1 realtime map the primary lidar source
This commit is contained in:
@@ -71,6 +71,30 @@ define the normalization.
|
||||
- The 1.27 m run makes the effect of the operator estimate visible and
|
||||
repeatable, but remains diagnostic-only.
|
||||
|
||||
## Architecture clarification — 2026-07-25
|
||||
|
||||
This ADR rejects one algorithm/input pairing. It does not reject K1 as the
|
||||
physical LiDAR, downgrade its real-time report stream to an offline-only source
|
||||
or require replacement hardware.
|
||||
|
||||
- `lio_pcl` and `lio_pose` were received while the handheld rig moved and are
|
||||
admitted as the primary real-sensor replay/shadow source.
|
||||
- The pose permits points to be expressed relative to the current pivot. It
|
||||
does not prove the original firing pose/time of every already mapped point.
|
||||
- The historical `1.27 m` value is never an operational constant. It remains
|
||||
only in the immutable Patchwork++ diagnostic identity.
|
||||
- A ground-vehicle profile estimates the local surface over time and derives
|
||||
sensor-to-surface height, slope and roughness from that surface. A free-flight
|
||||
profile uses 3D occupancy/clearance and may publish ground as unavailable.
|
||||
- A future fixed rig contributes `T_body_from_lidar`; it does not make height
|
||||
above terrain constant.
|
||||
- Persistent reconstruction and short-TTL perception are separate derivatives
|
||||
of the same immutable K1 evidence. Neither derivative rewrites the source.
|
||||
- Current work is passive: no K1 firmware change, onboard exporter, internal
|
||||
topic invocation or new application command is authorized.
|
||||
- `RAVNOVES00` is retained as an immutable private experimental dataset. All
|
||||
prior benchmark artifacts remain valid records of the investigated approach.
|
||||
|
||||
## Real diagnostic evidence
|
||||
|
||||
Benchmark
|
||||
|
||||
Reference in New Issue
Block a user