Introduced CoM randamization in manager based events.

[shendredm]

Description

Introduced CoM randomization in events.py for manager based envs. Individual range can be selected for individual axis and bodies.
Thanks to #641 and #693 for motivation of the code.

Type of change

• New feature (non-breaking change which adds functionality)
• This change requires a documentation update

Screenshots

Please attach before and after screenshots of the change if applicable.

Checklist

• [x] I have run the pre-commit checks with ./isaaclab.sh --format
• [ ] I have made corresponding changes to the documentation
• [x] My changes generate no new warnings
• [ ] I have added tests that prove my fix is effective or that my feature works
• [ ] 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

[shendredm]

Hi, I have modified this MR for IsaacLab 2.0.0. Could you please review them when you get a chance? Thanks

[ParlitsisG]

Hi, @shendredm,

I noticed that this method changes the center of mass (COM), but how does it adjust the inertia? Changing the COM from the default value seems to imply a non-uniform density distribution. I plan to use this method for a project involving the manipulation of a cube with non-uniform density, and I want to modify the inertial parameters accordingly. Could you please clarify if this approach remains physically consistent with reality?

[kellyguo11]

This change appears to have broken training for the locomotion environments. @shendredm could you double check the training? I'll revert the change in the environment for now.

[shendredm]

Thanks for flagging this, @kellyguo. I’ve identified the bug that was causing the training failure and have pushed a fix. Training for the locomotion environments is now working as expected. Let me know if you see any further issues.

[kellyguo11]

Awesome, thanks so much for the quick fix! I'll let CI run through the new PR and have it merged. would be great if you can also link #2557 in the PR when you put it together.