Saran Tunyasuvunakool

Results 178 comments of Saran Tunyasuvunakool

@madhephaestus we're close to releasing a compiler API for use cases like yours that allows for incremental modification of the model without having to go through an XML. Perhaps it...

While this isn't currently supported, the `Renderer` class is a pure Python helper. If you want, you should be able to fairly straightforwardly add this feature (and maybe consider sending...

Can't answer the AlphaFold question specifically, but those `Unable to initialize backend` messages aren't errors. They're only informational logs as XLA iterates through candidate backends until it finds one that...

Are all of your boxes overlapping at t=0? Usually an easy fix would be to just set box qpos to different places.

If I recall correctly the bowl SDF only generates contact points on the inner (concave) surface, so it's not suitable for use as a model for a hollow ball.

I'm still reasonably convinced that you can simulate this robot without modeling its internal mechanism in the same way as it's actually implemented in real hardware (and therefore not needing...

This should be done as a [resource provider](https://mujoco.readthedocs.io/en/stable/programming/extension.html#resource-providers).

Does this also affect the `simulate` program? (You can just download our prebuilt tarball and execute `simulate`.)

That is very strange... the two viewers share the same code. You aren't building your own Python bindings right?

OK, this is most likely because the Python bindings depend on GLFW via the `PyGLFW` package, while `simulate` gets it from the system. Could you please try editing [this file](https://github.com/google-deepmind/mujoco/blob/main/python/mujoco/viewer.py)...