Directly predict the relative transformation in one shot

Directly predict the relative transformation in one shot

r"""Create input arguments for a sparse tensor `the documentation <https://nvidia.github.io/MinkowskiEngine/sparse_tensor.html>`_. Convert a

Build the mapping from the joint name to joint index.

Return a tensor where each element has the absolute value taken from the, corresponding element of a, with sign taken from the corresponding

Function to set up multiple pybullet cameras in the simulated environment

Returns torch.sqrt(torch.max(0, x)) but with a zero subgradient where x is 0.

Convert rotations given as axis/angle to quaternions. Args: axis_angle: Rotations given as a vector in axis angle form,

Naive implementation of the Chamfer distance. Args: points1 (numpy array): first point set points2 (numpy array): second point s

Check if obj_pcd is inside the 2D projection of our collision geometry Args: obj_pcd (np.ndarray): N X 3 pointcloud array, to be

Create a list of modules with together constitute a single conv layer with non-linearity and optional batchnorm/groupnorm. Args:

Convert rotations given as Euler angles in radians to rotation matrices. Args: euler_angles: Euler angles in radians as tensor of sh

Run full global + local registration routine, using numpy array pointclouds as input Args: source_np (np.ndarray): Source pointcloud,

Find transform that transforms pose source to pose target :param pose_frame_target: :param pose_frame_source: :return:

Function to check if any points in a 3D pointcloud fall inside of the convex hull of a set of 3D points. A convex hull for the collision