scipy.spatial.transform.RigidTransform.

as_exp_coords#

RigidTransform.as_exp_coords()[source]#

Return the exponential coordinates of the transform.

This implements the logarithmic map that converts SE(3) to 6-dimensional real vectors.

This is an inverse of from_exp_coords where details on the mapping can be found.

Returns:
exp_coordsnumpy.ndarray, shape (…, 6)

Exponential coordinate vectors with the same leading dimensions as the transform. The first three components define the rotation and the last three components define the translation.

Notes

Array API Standard Support

as_exp_coords has experimental support for Python Array API Standard compatible backends in addition to NumPy. Please consider testing these features by setting an environment variable SCIPY_ARRAY_API=1 and providing CuPy, PyTorch, JAX, or Dask arrays as array arguments. The following combinations of backend and device (or other capability) are supported.

Library

CPU

GPU

NumPy

✅

n/a

CuPy

n/a

✅

PyTorch

✅

✅

JAX

✅

✅

Dask

⛔

n/a

See Support for the array API standard for more information.

Examples

>>> from scipy.spatial.transform import RigidTransform as Tf
>>> import numpy as np

Get exponential coordinates of the identity matrix:

>>> Tf.identity().as_exp_coords()
array([0., 0., 0., 0., 0., 0.])