fix(loader): unify joint order to canonical at zarr-build time - #3
Merged
Conversation
Make each NPZ's own `joint_names` the authoritative native order and add a `canonical_joint_names` option. At zarr-build time, joint-dim arrays (joint_pos/joint_vel/qpos/qvel and their next_* counterparts) are remapped native -> canonical (robot articulation order) and the store is labelled with the canonical order. Training then reads a single canonical layout, making the reference->target remap identity regardless of source ordering. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Make each NPZ's own
joint_namesthe authoritative native order and add acanonical_joint_namesoption. At zarr-build time, joint-dim arrays (joint_pos/joint_vel/qpos/qvel and their next_* counterparts) are remapped native -> canonical (robot articulation order) and the store is labelled with the canonical order. Training then reads a single canonical layout, making the reference->target remap identity regardless of source ordering.