Open
Conversation
Flova
reviewed
Apr 9, 2026
Member
Flova
left a comment
Flova
left a comment
There was a problem hiding this comment.
Thanks for this large setup. Looks very promising so far. I still have some feedback as seen below. You can reach out to be for further questions :)
jaagut
reviewed
Apr 12, 2026
| Position_D_Gain: 0 #2800 # [/16] 0~16,383 | ||
| Position_I_Gain: 0 #180000 # [/ 65,536] 0~16,383 | ||
| #If robot starts to tremble, reduce Position_P_Gain | ||
| Position_P_Gain: 1200 #1100 # [/ 128] 0~16,383 |
Member
There was a problem hiding this comment.
Why are we changing these P-gain values? Can we still walk as usual with this?
| servos: | ||
| # specifies which information should be read | ||
| read_position: true | ||
| read_velocity: false |
Member
There was a problem hiding this comment.
What are the velocities used for?
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This change provides a framework for rl policies. Main purpose is to minimize boiler plate code and facilitate the integration of rl models.
Proposed changes
I did a full replacement of bitbots_motion/bitbots_rl_motion.
Furthermore, I added an action called "RLKick" which can be found in kick_action. It should be used instead of WalkKick, however, it isn't fully finished, and thus, it isn't in use. Additionally, I created a capsule for rl kick.
Last, I expanded motion.launch accordingly (start command for policy nodes is currently excluded).
Related issues
Behavior should be fixed. Policies take action independant of the current game state. As an example: If you replace @WalkKick with @RLKick in dsd and include the start command for policies, the kick policy takes immediate action.
Checklist
pixi run build