Add Simplified MJCF Model for RBY1 Robot #134
Merged
Conversation
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
…ainbow robotics rby1 model.
…ainbow robotics rby1 model.
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
kevinzakka
approved these changes
Jan 4, 2025
Collaborator
kevinzakka
left a comment
kevinzakka
left a comment
There was a problem hiding this comment.
Amazing PR, thank you!
Contributor
Author
|
Dear Kevin Zakka,
I am Donghyeon Noh from Rainbow Robotics.
Last week, we submitted a pull request for the model of our robot, RBY1,
following the guidelines of the google-deepmind/mujoco_menagerie repository.
However, we encountered a failure due to the Google CLA (Contributor
License Agreement). To provide more context, I have attached two
screenshots illustrating the issue.
Could you kindly let us know what additional steps are required on our end
to resolve this? We are ready to take prompt action to address the matter.
Thank you for your support.
Best regards,
Donghyeon Noh
Rainbow Robotics
2025년 1월 4일 (토) 오전 10:01, Kevin Zakka ***@***.***>님이 작성:
… ***@***.**** approved this pull request.
Amazing PR, thank you!
—
Reply to this email directly, view it on GitHub
<#134 (review)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AWFL4WNHQPDSEDYQ6DHAMRT2I4XHFAVCNFSM6AAAAABURLFBYKVHI2DSMVQWIX3LMV43YUDVNRWFEZLROVSXG5CSMV3GSZLXHMZDKMRZHA2TSMJQGY>
.
You are receiving this because you modified the open/close state.Message
ID: ***@***.***
com>
|
Contributor
Author
|
Hello, we are the RBY1 Support Team from Rainbow Robotics. The previous MJCF model for the RBY1 robot did not include the joint torque limits. I will submit a new pull request with the revised file. Thank you for your attention. Best regards, |
Contributor
Author
|
Hi, @kevinzakka. We have completed the verification of the following for adding the RBY1 model:
Please review and merge the PR. |
Collaborator
|
Hi @dongridong, thank you! I'm in the process of wrapping up a project for release next week so will be able to take a look then! |
Contributor
Author
|
Dear Kevin Zakka,
I hope you're doing well.
I just wanted to follow up on the PR I submitted on 25.01.04. I understand
you’ve been busy, but I’d appreciate an update when you have a moment.
Let me know if there’s anything I can assist with.
Thank you!
Best regards,
Donghyeon Noh
2025년 1월 9일 (목) 오후 1:56, Kevin Zakka ***@***.***>님이 작성:
… Hi @dongridong <https://github.com/dongridong>, thank you! I'm in the
process of wrapping up a project for release next week so will be able to
take a look then!
—
Reply to this email directly, view it on GitHub
<#134 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AWFL4WMH7A6HB5V56WP3GLT2JX6PNAVCNFSM6AAAAABURLFBYKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDKNZZGE4DANBSGU>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
|
Collaborator
|
@dongridong Working on this today! |
saran-t
approved these changes
Jan 27, 2025
Contributor
Author
|
Dear Kevin Zakka,
I noticed an error occurring at the import/copybara line during the PR
process.
Could you clarify which specific part is causing the issue?
If you could point out the problematic part, I will make the necessary
corrections and submit the request again.
Thank you!
Best regards,
Donghyeon Noh
2025년 1월 27일 (월) 오후 10:30, Saran Tunyasuvunakool ***@***.***>님이
작성:
… ***@***.**** approved this pull request.
—
Reply to this email directly, view it on GitHub
<#134 (review)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AWFL4WKAY3PBZXSQ6FQKT2T2MYYHXAVCNFSM6AAAAABURLFBYKVHI2DSMVQWIX3LMV43YUDVNRWFEZLROVSXG5CSMV3GSZLXHMZDKNZVGQ2DGMZUGY>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
|
Collaborator
|
Working on getting this merged in, it's a huge PR! |
Collaborator
|
PR has been approved internally, it will get merged sometime today or tomorrow. Thanks for your patience @dongridong! |
copybara-service
bot
merged commit 2af6ce4
into
google-deepmind:main
2 of 3 checks passed
Collaborator
|
Hi @dongridong, looks like the model is not loadable in 3.2.7, getting include errors. |
Collaborator
|
This model needs a lot of work @dongridong, needs to go through another round of reviews. |
Contributor
Author
|
Could you please specify the issue you encountered?
The build test did not show any problems on my end.
If you can provide a clear description of the issue, I will make the
necessary modifications and share the updated version with you.
Thank you,
Dongridong
2025년 2월 19일 (수) 오전 8:14, Kevin Zakka ***@***.***>님이 작성:
… This model needs a lot of work @dongridong <https://github.com/dongridong>,
needs to go through another round of reviews.
—
Reply to this email directly, view it on GitHub
<#134 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AWFL4WMUWL5I3BD3N662KZT2QO5GLAVCNFSM6AAAAABURLFBYKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDMNRXGEZTIOJQGM>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
[image: kevinzakka]*kevinzakka* left a comment
(google-deepmind/mujoco_menagerie#134)
<#134 (comment)>
This model needs a lot of work @dongridong <https://github.com/dongridong>,
needs to go through another round of reviews.
—
Reply to this email directly, view it on GitHub
<#134 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AWFL4WMUWL5I3BD3N662KZT2QO5GLAVCNFSM6AAAAABURLFBYKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDMNRXGEZTIOJQGM>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
|
Collaborator
|
Contributor
Author
|
Hello,
This is dongridong.
First of all, I really appreciate your support.
I have reviewed the feedback you provided.
If you could share the modified file from your local environment, I will
incorporate the remaining changes and submit the PR again.
Best regards.
dongridong
2025년 2월 19일 (수) 오전 9:37, Kevin Zakka ***@***.***>님이 작성:
…
- On 3.2.7, the model does not load.We should switch from include to
attach. I can share my local modification if you wish.
- Actually modeling the wheels might not be necessary. We can attach 3
joints (x, y, z) to the base and actuate those. In any case, I don't think
we need to convex decompose the wheels, those aren't really participating
in any serious collision avoidance.
- Switch to implicitfast integrator.
- The joint damping and armature is really high. We need to tweak them
to much lower values.
—
Reply to this email directly, view it on GitHub
<#134 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AWFL4WKYFFKSRCQYIJ3H6332QPG5JAVCNFSM6AAAAABURLFBYKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDMNRXGIZTKMJWGA>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
[image: kevinzakka]*kevinzakka* left a comment
(google-deepmind/mujoco_menagerie#134)
<#134 (comment)>
- On 3.2.7, the model does not load.We should switch from include to
attach. I can share my local modification if you wish.
- Actually modeling the wheels might not be necessary. We can attach 3
joints (x, y, z) to the base and actuate those. In any case, I don't think
we need to convex decompose the wheels, those aren't really participating
in any serious collision avoidance.
- Switch to implicitfast integrator.
- The joint damping and armature is really high. We need to tweak them
to much lower values.
—
Reply to this email directly, view it on GitHub
<#134 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AWFL4WKYFFKSRCQYIJ3H6332QPG5JAVCNFSM6AAAAABURLFBYKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDMNRXGIZTKMJWGA>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
|
Contributor
Author
|
Dear @kevinzakka,
I hope you are doing well.
Here is a summary of the changes made locally so far:
1. I am currently waiting for the updated files from your local setup.
Once I receive them, I plan to incorporate the modifications listed below.
2. I have removed all collision files for the wheels while keeping the
visual representation unchanged.
3. I have added the implicitfast integrator as an option.
4. The following parameters have been adjusted:
- armature: 10 → 0.01
- damping: 50 → 5
Once you share the updated files, I will make further parameter adjustments
and send them back to you.
Looking forward to your response.
Best regards,
Dongridong
2025년 2월 19일 (수) 오전 9:37, Kevin Zakka ***@***.***>님이 작성:
…
- On 3.2.7, the model does not load.We should switch from include to
attach. I can share my local modification if you wish.
- Actually modeling the wheels might not be necessary. We can attach 3
joints (x, y, z) to the base and actuate those. In any case, I don't think
we need to convex decompose the wheels, those aren't really participating
in any serious collision avoidance.
- Switch to implicitfast integrator.
- The joint damping and armature is really high. We need to tweak them
to much lower values.
—
Reply to this email directly, view it on GitHub
<#134 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AWFL4WKYFFKSRCQYIJ3H6332QPG5JAVCNFSM6AAAAABURLFBYKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDMNRXGIZTKMJWGA>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
[image: kevinzakka]*kevinzakka* left a comment
(google-deepmind/mujoco_menagerie#134)
<#134 (comment)>
- On 3.2.7, the model does not load.We should switch from include to
attach. I can share my local modification if you wish.
- Actually modeling the wheels might not be necessary. We can attach 3
joints (x, y, z) to the base and actuate those. In any case, I don't think
we need to convex decompose the wheels, those aren't really participating
in any serious collision avoidance.
- Switch to implicitfast integrator.
- The joint damping and armature is really high. We need to tweak them
to much lower values.
—
Reply to this email directly, view it on GitHub
<#134 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AWFL4WKYFFKSRCQYIJ3H6332QPG5JAVCNFSM6AAAAABURLFBYKVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDMNRXGIZTKMJWGA>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
|
donghoon11
pushed a commit
to donghoon11/mujoco_menagerie
that referenced
this pull request
May 7, 2025
…cs_rby1 PiperOrigin-RevId: 728357370 Change-Id: I86152acd8027906ea0eb97db0b08779ad2882346
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.
Hello, we are the RBY1 Support Team from Rainbow Robotics.
We would like to contribute a simplified MJCF model for the RBY1 robot to support its use in simulations.
Description:
This pull request introduces a simplified MJCF description of the RBY1 robot developed by Rainbow Robotics. The model includes:
Preprocessed meshes and assets for efficient simulation.
A well-defined rby1.xml MJCF file that:
Implements the robot's structure and actuator configurations.
Adjusts joint and collision properties for optimal MuJoCo simulation.
Compatibility with the original URDF file, enabling smooth transitions between formats.
Key Features:
Preprocessed meshes optimized for MuJoCo.
Support for free joint movement in 3D space.
Streamlined collision handling using classes.
License:
This model is distributed under the Apache License 2.0.
If merged, this addition will provide researchers and developers with enhanced simulation tools for the RBY1 robot.
If you have any questions, please feel free to contact us at [email protected].
Thank you!