Skip to content

docs(sessions): record the end-to-end R-IEKF EuRoC harness day - #431

Merged
Ravenwater merged 1 commit into
mainfrom
docs/session-2026-06-30-riekf-euroc-harness
Jul 1, 2026
Merged

docs(sessions): record the end-to-end R-IEKF EuRoC harness day#431
Ravenwater merged 1 commit into
mainfrom
docs/session-2026-06-30-riekf-euroc-harness

Conversation

@Ravenwater

@Ravenwater Ravenwater commented Jul 1, 2026

Copy link
Copy Markdown
Contributor

Summary

Day wrapup for #429 — the end-to-end R-IEKF EuRoC harness.

  • Session log docs/sessions/2026-06-30-riekf-euroc-harness.md — the arc, the two real-data bugs the harness surfaced (SqrtCovariance divergence → Joseph FullCovariance; non-finite-δx update guard), the measured MSCKF-vs-R-IEKF 2×2, and the load-bearing finding.
  • CHANGELOG milestone entry (top of ## Milestones), linking the session log, marked main, post-v0.65.0 (feat(tools): drive R-IEKF through the real EuRoC pipeline #429 landed after the v0.65.0 release PR, currently unreleased).

The finding, in one line

R-IEKF runs stably end to end but underperforms the body-frame MSCKF (ATE 1.3 m vs 0.27 m; position ATE/σ 17–19 vs 2.1) — and position-norm ATE/σ cannot test the yaw-gauge thesis (standard MSCKF is already ~calibrated at 2.1 on position, since the leak is rotational). A gauge-anchored attitude-NEES is the #365 follow-up.

Changes

  • docs/sessions/2026-06-30-riekf-euroc-harness.md — new session log
  • CHANGELOG.md — new milestone entry

Docs only — no code changes.

Relates to #365

🤖 Generated with Claude Code

Summary by CodeRabbit

  • Documentation
    • Added a new session note describing an end-to-end R-IEKF EuRoC harness evaluation, including stability observations, reported error metrics, and next-step notes.
    • Updated the changelog with a new milestone entry for 2026-06-30, linking to the session write-up and summarizing the latest harness results.

Session log + CHANGELOG milestone for #429: the R-IEKF backend driven
through the validated front end on real EuRoC, measured against the
standard MSCKF. R-IEKF runs stably (Joseph FullCovariance) but
underperforms on ATE and position-σ; the load-bearing finding is that
position-norm ATE/σ cannot test the yaw-gauge thesis — a gauge-anchored
attitude-NEES is the #365 follow-up.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@coderabbitai

coderabbitai Bot commented Jul 1, 2026

Copy link
Copy Markdown

Review Change Stack

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: ASSERTIVE

Plan: Pro

Run ID: 9b84cec7-0ffd-460e-a3a7-052a40ed427e

📥 Commits

Reviewing files that changed from the base of the PR and between 3c6f4f5 and 34107ee.

📒 Files selected for processing (2)
  • CHANGELOG.md
  • docs/sessions/2026-06-30-riekf-euroc-harness.md

Walkthrough

This PR adds a CHANGELOG milestone entry and a new session document recording an end-to-end R-IEKF EuRoC harness evaluation. It describes harness components, two real-data bugs found (covariance representation, non-finite update handling), measured ATE/σ results, and follow-up work.

Changes

R-IEKF EuRoC Harness Session Documentation

Layer / File(s) Summary
CHANGELOG milestone entry
CHANGELOG.md
Adds a 2026-06-30 milestone bullet describing the harness run, stability/metric comparisons, and linking to the session doc.
Session intro and harness build
docs/sessions/2026-06-30-riekf-euroc-harness.md
Documents session motivation, harness components (adapter, runner, calibration, gate test), and two real-data bugs found with their mitigations.
Results, discoveries, and status
docs/sessions/2026-06-30-riekf-euroc-harness.md
Reports ATE/σ comparison results, metric-validity discoveries, implementation guidance, PR merge status, and next steps (attitude-NEES metric).

Estimated code review effort: 1 (Trivial) | ~3 minutes

Possibly related PRs

  • branes-ai/cortex#369: Updates the same CHANGELOG and adds a similar docs/sessions/* page documenting the same R-IEKF development arc, including the shared #365 yaw-gauge follow-up.

Poem
A rabbit hopped through EuRoC's maze,
Tracked R-IEKF's stability craze,
Joseph-form covariance saved the day,
Non-finite δx turned away,
Logged in docs for future gaze. 🐇📜

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Title check ✅ Passed The title is Conventional Commits formatted and accurately summarizes the docs-only harness-day update.
Description check ✅ Passed The description covers Summary, Changes, and Linked issue, but it omits the template's Test Results and Checklist sections.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch docs/session-2026-06-30-riekf-euroc-harness

Comment @coderabbitai help to get the list of available commands.

@Ravenwater Ravenwater self-assigned this Jul 1, 2026
@Ravenwater Ravenwater added this to the Phase 3: VIO milestone Jul 1, 2026
@Ravenwater
Ravenwater marked this pull request as ready for review July 1, 2026 02:42
@Ravenwater
Ravenwater merged commit 2ba9a30 into main Jul 1, 2026
15 checks passed
@Ravenwater
Ravenwater deleted the docs/session-2026-06-30-riekf-euroc-harness branch July 1, 2026 02:52
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant