Add low-pass filter to make robot actions smooth. Integrated into ACT and DP. #760
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
|
Nice work! By any chance do you have videos? Before vs After ? |
|
@Cadene The before vs after demo for action smoothing. Its more prominent for DP than ACT. before_action_smoothing.mp4after_action_smoothing.mp4 |
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Outdated suggestions cannot be applied.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.
What this does
Adds low-pass filter (Butterworth filtering) to actions from the policy. Prevents jerky motion of the robot during eval. Tried out different techniques but the method provided noticeable improvement. I have tuned the filter parameters to be subtle and not too aggressive.
(⚡️ Performance)
How it was tested
Tested on rollouts of both ACT and Diffusion policy trained on my custom dataset. Used SO-100 Arm for my setup. Noticeable difference in the robot motion smoothness especially for Diffusion Policy.
How to checkout & try? (for the reviewer)
Try evaluating ACT and DP on your robot. This PR integrates the smoothen_actions func in ACT and DP policy implementation so there is nothing extra to be done.