Repository navigation
Publish measured hardware reference and calibration roadmap - #22
Merged
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds a public hardware-matching paper and complete CPU diagnostics for the separately implemented UR5e/Robotiq reference. It connects exact mechanical contracts, explicit calibration gaps, paired replay scoring and future LeRobot collection with an original DVIDIA policy. The homepage, topic readers and feed expose the new publication.
All 18 unloaded numerical attempts are retained. At a 1 ms step, measured physics throughput is 40.80–47.29× elapsed time on one host; loading, vision, policy and physical actuation are excluded. Moving-link collisions and gripper coupling are represented, while the fixed-base collision gap, privileged sensing, unmeasured hardware fidelity, missing shoe policy and future bimanual assembly remain explicit.
Validation: 35 research tests, generated catalog/readers/link checks and deployment dry run pass. Measurement artifacts match the frozen training bundle; runtime source is pinned to c95a4385dae4b654b01ef75f56cbcc144fde2f5c. The offline bench passed desktop/mobile controls and replay checks. Contributor attribution remains empty; DVIDIA contact and X profile remain the publication identity.