adding threshold to consider to other critics to disable on approach to goal + retune a little #95
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
…to goal + retune a little
artofnothingness
requested changes
Oct 6, 2022
Co-authored-by: Alex <[email protected]>
Co-authored-by: Alex <[email protected]>
|
Done! |
artofnothingness
approved these changes
Oct 6, 2022
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Outdated suggestions cannot be applied.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.
In further response to #79
This helps make sure that we disable the critics that can create local-minima near goals are disabled closer to the goal poses. Rather than setting it to the positional tolerance (which could be 0.1-0.3m), we decouple when we stop considering these critics from the actual positional tolerance itself so a larger window around goals can be incentivized to focus on the relevant critics (collision, goal, goal angle).
I found that this (and tuning some of the weights a little more, which I later realized were off because my files were outdated 😆 ) to increase the convergence to goal to nearly every time and doing so in a more direct way with less confusion.
Even after these changes #79 needs to stay open until we can do testing on hardware to make sure that these changes and the previous work by @artofnothingness is sufficient.