-
Notifications
You must be signed in to change notification settings - Fork 1.6k
Adds body_pose_w and body_projected_gravity_b observations #2212
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Adds body_pose_w and body_projected_gravity_b observations #2212
Conversation
""" | ||
|
||
|
||
def link_pose( |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can we simply call it body_pose_w? What happens if user specifies a list of body ids? I think their flattned version should be given?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Instead of link_name
they must use body_names
in asset config IMO.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
yeah body_pose_w is fine, and body_name is fine. I will switch to body vs link everywhere. (old habit to use link).
As far as the body_ids goes currently this observation will only produce one body driven by (link_name/body_name argument). if the users doesn't set the link name it will grab only the zeroth entry specified in the resolved SceneEntityCfg. So if they specify a list of body_ids they can only pick one of them.
I could see creating it in a way that all body_ids specified in the asset_cfg are provided in a flattened tensor, but this wasn't my original intention.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think flattening it is the most general way to go. If they want the "zeroth" body which is the root, then they should use the root_
alternative functions.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thats valid. I will rework it.
Description
This PR add body_pose_w and body_projected_gravity_b observation methods
Fixes # (issue)
Type of change
Checklist
pre-commit
checks with./isaaclab.sh --format
config/extension.toml
fileCONTRIBUTORS.md
or my name already exists there