Fanbo Xiang

You can try `set_qf` every step. ```python self.robot.set_drive_target(action) print("action:",action) qf = self.robot.compute_passive_force(gravity=True, coriolis_and_centrifugal=True) self.robot.set_qf(qf) for i in range(self.frame_skip): # add these lines qf = self.robot.compute_passive_force(gravity=True, coriolis_and_centrifugal=True) self.robot.set_qf(qf) self.scene.step() self.render() self.current_step...

All geometries in SAPIEN are mesh so there is no GT point cloud. I guess you could mean 2 things. 1. Point cloud from GT depth map of cameras. This...

Can you start a new issue and post the result of `vulkaninfo` and `nvidia-smi`?

Assuming you are using SAPIEN 2.x. If you need a snapshot of the collision or visual meshes of an articulation with the current state. You may find this script helpful....

Hi, I have extensively tested remote visualization recently and here are the findings. First, Vulkan does not officially support any kind of X-forwarding, so I cannot guarantee that remote visualization...

You may try passing `offscreen_only=True` to `SapienRenderer` constructor. This behavior will be changed in the future (to make CUDA device take higher priority than on-screen rendering)

I cannot figure out what is causing the issue. I think you should set the pci id of the device you want to use directly. This method requires a bit...

Are you using `sapien==2.2.2`? I have verified that the GPU selection feature is working. You can try `sapien.SapienRenderer.set_log_level("info")` before creating the renderer. It will list all available GPUs to the...

The PartNet-Mobility dataset does not provide any point cloud files. This is a dataset providing articulated models in the URDF format. If you would like to render partial point cloud,...

Did you set `cuda:2` in your torch code or did you set `CUDA_VISIBLE_DEVICES=2`? `CUDA_VISIBLE_DEVICES=2` will make the GPU with index 2 to become `cuda:0`.