Replies: 1 comment
-
|
Thank you for sharing the list of reference projects that offer differentiable physics! At the moment, we do not support differentiable arithmetic, as it requires extensive engineering effort. I believe the core mathematics are already fairly clear; what makes it difficult is mostly the engineering itself. With the recent advances in coding agents, I hope this may eventually become a much simpler matter with far less human labor involved. Since the entire codebase is licensed under Apache 2.0, I also humbly hope that some follow-up work from the community may eventually do this for us. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Hi @ryichando,
Thank you for a very cool repo, which may be among the best OOS engines for contact-solving imo.
Just in case of a possibility that the engine can be made differentiable in the future, these may be of relevance:
C++
https://simple-robotics.github.io
https://github.com/Simple-Robotics/Simple
https://spirimirror.github.io/libuipc-web
https://github.com/InteractiveComputerGraphics/stark
Rust
https://github.com/ecto/phyz
https://github.com/ecto/tang
https://github.com/djrakita/ad_trait
Python
https://github.com/newton-physics/newton
https://github.com/google/brax
https://github.com/Genesis-Embodied-AI/Genesis
Further here
https://github.com/curieuxjy/Awesome_Manipulation/blob/main/Learning.md
Thank you!
Beta Was this translation helpful? Give feedback.
All reactions