Add dynamic scene recovery for atomic actions - #450
Open
yuecideng wants to merge 2 commits into
Open
Conversation
Add versioned scene providers, per-environment collision-world invalidation, and planner-side dynamic obstacle binding. Include bounded recovery tests plus runnable moving-target and cuRobo obstacle examples.
yuecideng
force-pushed
the
feat/atomic-action-pr2a-execution-runner
branch
from
August 3, 2026 03:37
1794d02 to
00456c8
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
This PR adds dynamic-scene recovery to the typed atomic-action execution stack.
It introduces a
SceneProviderboundary, aRigidObjectSceneProvider, global/per-environment collision-world revisions, and collision-sensitive phase invalidation.AtomicAction.plan()now owns scene binding and delegates skill logic to_plan(), so current obstacle poses are injected into copied planner options instead of being repeated across individual skill parameters. cuRobo implements the dynamic-world bridge, andExecutionSessionemitscollision_world_changedbefore bounded per-environment replanning.The PR also adds runnable moving-target and dynamic-obstacle recovery tutorials, focused multi-environment recovery tests, planner/provider tests, and corresponding Sphinx and agent-context updates.
Dependencies: #449. This is a stacked PR whose base is
feat/atomic-action-pr2a-execution-runner; commit7cbba908is the PR2B-only change.Fixes: N/A (no linked issue).
Type of change
The extension hook for
AtomicActionsubclasses changes from overriding publicplan()to implementing_plan(). This is intentional within the unmerged refactor stack and prevents actions from bypassing framework-owned scene binding.Validation
black --check --diff --color ./— 562 files unchangedpytest -q tests/sim/atomic_actions tests/sim/planners/test_curobo_planner.py tests/sim/planners/test_motion_generator_batched.py— 181 passed, 4 skippedpython -m compileall -q embodichain/lab/sim/atomic_actions scripts/tutorials/atomic_actionagent_context/MAP.yamlYAML parsingdynamic_goal_changed→replanned→ completed after 83 accepted commandscollision_world_changed→replanned→ completed after 83 accepted commandsScreenshots
Not applicable; this change adds runtime APIs and headless simulation tutorials.
Checklist
black .command to format the code base.