Repository navigation
refactor(rl): restore deformable timing and retain generic state mirror - #11
Merged
Merged
Conversation
|
Caution Review failedThe pull request is closed.
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Restore deformable transformer deployment on the simplified bridge: history sampling runs at 100 Hz while policy submission runs at 200 Hz, delayed previous actions follow the observation submission tick, and flat hold executes and feeds back zero. Validity is a bool; inference faults remain latched until an explicit reset. Startup validates rate divisibility and exact ONNX contracts.
Retain the generic YAML-driven StateMirror, move formatting and ROS publishing to its own thread, preserve the existing topics/QoS/stamp/manifest contract, and repair duplicate keys in legacy v1 replay conversion. Add a vehicle-independent offline policy checker, Chinese troubleshooting, and portable model receipts. The 16001 fallback model remains available; no accepted jump model is bundled by this change.
Validation: container build; 200,000-tick comparison against ccdeb79; 87,848 wheel-leg observation frames with zero feature error; hardware-message and full/gimbal component graph regressions; metadata and mirror type rejection; four ROS message classes field-identical across synchronous/threaded/50 ms busy publication; deformable graph and 2048-sample bitwise ONNX migration parity; policy checker positive and negative cases; legacy/generic mirror replay tests. All runs are offline and use fake feedback or explicit pilot fixtures.
The deployment requires the executor initialization-order correction on RMCS branch feat/executor-stepped-clock (71e6f8f). The wheel-leg integration branch has been rebased onto that branch, as requested; RMCS PR #105 was closed instead of merging that correction into main.
The superseded export/prepare tools and the old simulation host remain until their replacements have landed and their required verification is complete.