Get rotation from transform

Get translation from transform

Random pushes the robots. Emulates an impulse by setting a randomized base velocity.

Takes some iterable that might contain iterables and converts it to a list of lists [of lists... etc] Mainly used for converting the st

Contract the array of `cls` to the size of `subcls`.

Expand the array of `subcls` to the size of `cls`.

Construct a skeleton motion from a skeleton state. The velocities are estimated using second order guassian filter along the last axi

w x y z Convert rotations given as rotation matrices to quaternions. Args: matrix: Rotation matrices as tensor of shape (..., 3,

Load the mesh from the XML file and merge them into the humanoid based on the current pose.

Create a 3D rotation from angle and axis of rotation. The rotation is counter-clockwise along the axis. The rotation can be interpreted as a_

Construct a 3D rotation from a valid 3x3 rotation matrices. Reference can be found here: http://www.cg.info.hiroshima-cu.ac.jp/~miyazaki/

Construct identity 3D rotation with the same shape

quaternion multiplication

Multiply two quaternions. Usual torch rules for broadcasting apply. Args: a: Quaternions as tensor of shape (..., 4), real part

Multiply two quaternions. Usual torch rules for broadcasting apply. Args: a: Quaternions as tensor of shape (..., 4), real part

WXYZ Convert rotations given as quaternions to rotation matrices. Args: quaternions: quaternions with real part first,

Convert rotations given as quaternions to rotation matrices. Args: quaternions: quaternions with real part first, as ten

Retarget the skeleton state to a target skeleton tree. This is a naive retarget implementation with rough approximations. The functi

Sets the root state tensor for specified actors within environments. Args: set_env_ids (tensor): Tensor of environment I

Sets the DOF state tensor for specified actors within environments. Args: set_env_ids (tensor): Tensor of environment ID

Move data in the batch to cuda(), carefully handle data that is not tensor

Inverse transformation

Combine two transformation together

Updates the camera view pose based on the current viewer origin and the eye and lookat positions. Args: eye: The eye position of

model: The original PyTorch model. input_keys: List of input names as keys for the input dictionary.

Extract the first or third Euler angle from the two members of the matrix which are positive constant times its sine and cosine. Args:

Extract the first or third Euler angle from the two members of the matrix which are positive constant times its sine and cosine. Args: