Fixes body IDs selection when computing feet_slide reward for locomotion-velocity task
#1277
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
dtc103
requested review from
Dhoeller19,
Mayankm96,
jsmith-bdai,
jtigue-bdai and
kellyguo11
as code owners
dtc103
changed the title
dtc103
changed the title
Mayankm96
changed the title
feet_slide reward for locomotion-velocity task
Mayankm96
reviewed
Oct 21, 2024
Mayankm96
approved these changes
Oct 21, 2024
Mayankm96
reviewed
Oct 22, 2024
Signed-off-by: Mayank Mittal <12863862+Mayankm96@users.noreply.github.com>
Signed-off-by: Mayank Mittal <12863862+Mayankm96@users.noreply.github.com>
iamdrfly
pushed a commit
to iamdrfly/IsaacLab
that referenced
this pull request
Nov 21, 2024
…otion-velocity task (isaac-sim#1277) # Description Since I wanted to use Isaac Lab for training a Unitree Go2, I played around with the examples to get used to the framework. While playing around, I got the following error message: ``` reward = torch.sum(body_vel.norm(dim=-1) * contacts, dim=1) RuntimeError: The size of tensor a (19) must match the size of tensor b (4) at non-singleton dimension 1 ``` The reward term was added as follows: ``` sliding_feet = RewTerm( func=mdp.feet_slide, params={"sensor_cfg": SceneEntityCfg("contact_forces", body_names=".*foot")}, weight=0.1 ) ``` After some code investigation, I found out, that inside the feet_slide function, the body velocities are queried as "asset.data.body_lin_vel_w[:, asset_cfg.body_ids, :2]". This would return the velocity of all body parts, since asset_cfg.body_ids contains the ids of all body parts. Therefore we need to change the line to "body_vel = asset.data.body_lin_vel_w[:, sensor_cfg.body_ids, :2]" since we only want the velocity of the body parts that contain the force sensors. This means we have to change `asset_cfg.body_ids` to `sensor_cfg.body_ids` inside the tensor call Doing this leads to the successful running of the simulation without failure. No additional dependencies are necessary for this fix. ## Type of change - Bug fix (non-breaking change which fixes an issue) ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] My changes generate no new warnings - [ ] I have added tests that prove my fix is effective or that my feature works - [x] I have updated the changelog and the corresponding version in the extension's `config/extension.toml` file - [x] I have added my name to the CONTRIBUTORS.md or my name already exists there
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
Since I want to use Isaac Lab for training a Unitree Go2, I was playing around with the examples to get used to the framwork. While playing around, I got the following error message:
The reward term was added as follows:
After some code investigation, I found out, that inside the feet_slide function the body velocities are queried as "asset.data.body_lin_vel_w[:, asset_cfg.body_ids, :2]". This would return the velocity of all body parts, since asset_cfg.body_ids contains the ids of all body parts.
Therefore we need to change the line to "body_vel = asset.data.body_lin_vel_w[:, sensor_cfg.body_ids, :2]" since we only want the velocity of the body parts that contain the force sensors.
This means we have to change
asset_cfg.body_idstosensor_cfg.body_idsinside the tensor callDoing this lead to successfully running the simulation without failure.
No additional dependencies are necessary for this fix.
Type of change
Screenshots
Please attach before and after screenshots of the change if applicable.
Checklist
pre-commitchecks with./isaaclab.sh --formatconfig/extension.tomlfile