Refactor to support expanded Simulator reset in RearrangeTask #2018
Conversation
This file contains 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
…g after expanded state reset
aclegg3
requested review from
akshararai,
xavierpuigf,
ASzot,
jimmytyyang and
0mdc
facebook-github-bot
added
the
CLA Signed
0mdc
approved these changes
Aug 20, 2024
| @@ -243,8 +243,11 @@ def reset(self, episode: Episode, fetch_observations: bool = True): | |||
| self._is_episode_active = True | |||
|
|
|||
| if self._should_place_articulated_agent: | |||
| # here we are randomizing the base pos and rotation if necessary | |||
There was a problem hiding this comment.
That config field name is ambiguous. It may be worth the trouble renaming (not in this PR).
There was a problem hiding this comment.
Yeah, this part of the code is ripe for refactor
| for agent_idx in range(self._sim.num_articulated_agents): | ||
| self._set_articulated_agent_start(agent_idx) | ||
| # here we are setting initial joint states and such from configs, if a configured fixed base start state was provided, it is set | ||
| self._sim.agents_mgr.post_obj_load_reconfigure() |
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Outdated suggestions cannot be applied.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.
Motivation and Context
This PR aims to refactor RearrangeTask to support the expanded reset functionality from facebookresearch/habitat-sim#2451
Primary change: apply auto-sleep and handle articulated_agent base setting after expanded state reset
Context: previously the Simulator.reset() only set time to 0, so RearrangeTask code was able to leave the robot in place between reset and objects would stay sleeping (e.g. for benchmarking or idle scenarios). Now the objects are set to origin or scene_instance initial state and the reset logic must also handle initial state resetting and re-sleeping (since objects wake when moved).
How Has This Been Tested
Previously the hab2_benchmark test was failing due to regression because the robot was resetting to the origin inside a furniture and objects were awoken on initial reset.
I expect to see the CI pass to validate the change.
Types of changes
Checklist