mirror of https://github.com/azaion/gps-denied-onboard.git synced 2026-06-21 06:51:12 +00:00

Files

T

Oleksandr Bezdieniezhnykh 94d2358c8b [AZ-918] [AZ-919] [AZ-920] [AZ-921] [AZ-922] VIO/ESKF baseline fixes

Derkachi e2e Tier-2 divergence had three stacked root causes; this
commit ships fixes for all three plus the IMU prerequisite they
depend on, plus a baseline cheirality gate for cv2.recoverPose.

AZ-918  MAVLink IMU adapters now convert raw mG/mrad-s + FRD body to
        SI m/s^2 + rad/s + FLU body via helpers.imu_units. Without
        this the ESKF receives values ~1000x too small with wrong-
        sign Y/Z and cannot function at all.

AZ-919  Composition root wires EskfNominalAltitudeProvider into the
        KLT/RANSAC strategy via the AZ-331 factory introspect path;
        OKVIS2 and VINS-Mono are unaffected.

AZ-920  KLT/RANSAC recovers metric translation via Ground Sampling
        Distance when AGL is available; otherwise falls through with
        scale_quality=direction_only/unknown (no fake scale invented).

AZ-921  VioOutput.scale_quality signal; ESKF add_vio adapts R_meas
        position block based on the flag (1e6 inflation when scale is
        direction_only/unknown to keep the filter consistent).

AZ-922  KLT/RANSAC cheirality gate rejects single-frame rotations
        beyond a config threshold (default 30 deg), catching
        cv2.recoverPose twisted-pair flips that cause immediate ESKF
        divergence on low-parallax aerial scenes.

Verification:
- Tier-1 (macOS) unit suite: 2346 passed, 0 failed.
- Tier-2 (Jetson) Derkachi e2e: divergence moves from frame 5
  (mahalanobis^2 3757) to frame 233 (mahalanobis^2 212). Remaining
  drift is open-loop attitude accumulation, not cheirality.

Follow-up tickets filed:
- AZ-923 closed as misdiagnosed: EskfNominalAltitudeProvider was
  already correct (nominal_pos.z IS the AGL when takeoff origin sits
  at ground level); the early-frame AGL near zero reflects the drone
  being stationary on the ground, not a provider bug.
- AZ-942 filed: cross-check VIO rotation against IMU preintegrator
  (consistency gate) - more physically grounded than the coarse
  AZ-922 threshold and likely required to absorb the frame-233 drift.

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-05-27 22:28:40 +03:00

667 B

Raw Blame History

Autodev State

Current Step

flow: existing-code step: 10 name: Implement status: in_progress sub_step: phase: 9 name: out-of-band-bugfix detail: "F4 GSD scale recovery in TIER-2 VERIFICATION. AZ-919/920/921 all In Testing in Jira; Tier-1 (macOS) 2331 unit tests green. Jetson harness running 2026-05-27T14:06Z (rsync+image build+e2e). Awaiting pytest summary for the 4 previously-failing Derkachi tests (test_ac1_exits_0_jsonl_count_match, test_ac5_determinism_two_runs_diff, test_ac6_pace_realtime_60s_within_5pct, test_ac6_pace_asap_under_30s). AZ-918 sibling IMU fix is implicitly verified by the same Jetson run." retry_count: 0 cycle: 4 tracker: jira

667 B Raw Blame History

Autodev State

Current Step

667 B

Raw Blame History