feat(imitation): add direct OpenYAM teach collection - #3921
Draft
TomCC7 wants to merge 8 commits into
Draft
Conversation
❌ 11 Tests Failed:
View the top 3 failed test(s) by shortest run time
View the full list of 2 ❄️ flaky test(s)
To view more test analytics, go to the Test Analytics Dashboard |
TomCC7
commented
Sep 4, 2026
TomCC7
commented
Sep 4, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This is layer 6 of the OpenYAM learning slice. It replaces the closed A1Z learning-workflow PR #3318 as the top layer above #3855.
Contribution path
Problem
OpenYAM data collection currently requires a Quest teleoperator. Operators need a simpler scheme where they can put the arm in gravity-compensation mode, move it and the gripper by hand, and collect demonstrations without a second control device.
Solution
(2, 2, 2, 0.5, 0.5, 0.5).learning-collect-teach-openyamwith the native MCAP recorder, episode monitor, control coordinator, and wrist camera; keep Quest collection unchanged.dimos collect, a Textual operator dashboard with a recording timer, saved/discarded counters, contextual guidance, keyboard shortcuts, and clickable Start/Save, Discard, and Detach controls. It refuses to detach during an active take and never stops the daemon.OPENYAM_TEACH_LEARNING_PROFILE, which uses continuous measured joint state for both observations and kinesthetic actions. Quest collection keeps using accepted position commands.Learning slice
How to Test
dimos --can-port follower_l run learning-collect-teach-openyam --daemon \ --task "pick up the red block" \ --WristCamera.hardware.camera-index 0 \ --nativecollectionrecorder.store.path data/recordings/openyam-teach.mcap dimos collect dimos dataprep build \ --source data/recordings/openyam-teach.mcap \ --profile dimos.robot.manipulators.openyam.learning:OPENYAM_TEACH_LEARNING_PROFILE \ --output data/datasets/openyam-teachAI assistance
OpenAI Codex with GPT-5 assisted with implementation, tests, documentation, and PR preparation. The change was validated with the focused suites listed above.
Checklist