curobo.types.math module

class Pose(
position: Tensor | None = None,
quaternion: Tensor | None = None,
rotation: Tensor | None = None,
batch: int = 1,
n_goalset: int = 1,
name: str = 'ee_link',
normalize_rotation: bool = True,
)

Bases: Sequence

Pose representation used in CuRobo. You can initialize a pose by calling pose = Pose(position, quaternion).

position: Tensor | None = None

Position is represented as x, y, z, in meters

quaternion: Tensor | None = None

Quaternion is represented as w, x, y, z.

rotation: Tensor | None = None

Rotation is represents orientation as a 3x3 rotation matrix

batch: int = 1

Batch size will be initialized from input.

n_goalset: int = 1

Goalset will be initialized from input when position shape is batch x n_goalset x 3

name: str = 'ee_link'

name of link that this pose represents.

normalize_rotation: bool = True

quaternion input will be normalized when this flag is enabled. This is recommended when a pose comes from an external source as some programs do not send normalized quaternions.

static from_matrix(
matrix: ndarray | Tensor,
)
get_rotation()
stack(
other_pose: Pose,
)
repeat(n)

Repeat pose

Parameters:

n ([type]) – [description]

unsqueeze(dim=-1)
repeat_seeds(num_seeds: int)
get_index(
b: int,
n: int | None = None,
) → Pose
apply_kernel(kernel_mat)
classmethod from_list(
pose: List[float],
tensor_args: TensorDeviceType = TensorDeviceType(device=device(type='cuda', index=0), dtype=torch.float32, collision_geometry_dtype=torch.float32, collision_gradient_dtype=torch.float32, collision_distance_dtype=torch.float32),
q_xyzw=False,
)
classmethod from_batch_list(
pose: List[List[float]],
tensor_args: TensorDeviceType,
q_xyzw=False,
)
to_list(q_xyzw=False)
tolist(q_xyzw=False)
clone()
to(
tensor_args: TensorDeviceType | None = None,
device: device | None = None,
)
get_matrix(
out_matrix: Tensor | None = None,
)
get_numpy_matrix()
inverse()

Inverse of pose

Returns:

inverse pose

Return type:

Pose

get_pose_vector()
copy_(
pose: Pose,
)

Copies pose data from another memory buffer. This will create a new instance if buffers are not same shape

Parameters:

pose (Pose) – _description_

static cat(
pose_list: List[Pose],
)
distance(
other_pose: Pose,
use_phi3: bool = False,
)
angular_distance(
other_pose: Pose,
use_phi3: bool = False,
)

This function computes the angular distance phi_3.

See Huynh, Du Q. “Metrics for 3D rotations: Comparison and analysis.” Journal of Mathematical Imaging and Vision 35 (2009): 155-164.

Parameters:

  • goal_quat – _description_

  • current_quat – _description_

Returns:

Angular distance in range [0,1]

linear_distance(
other_pose: Pose,
)
multiply(
other_pose: Pose,
)
transform_point(
points: Tensor,
out_buffer: Tensor | None = None,
gp_out: Tensor | None = None,
gq_out: Tensor | None = None,
gpt_out: Tensor | None = None,
)
transform_points(
points: Tensor,
out_buffer: Tensor | None = None,
gp_out: Tensor | None = None,
gq_out: Tensor | None = None,
gpt_out: Tensor | None = None,
)
batch_transform_points(
points: Tensor,
out_buffer: Tensor | None = None,
gp_out: Tensor | None = None,
gq_out: Tensor | None = None,
gpt_out: Tensor | None = None,
)
property shape
compute_offset_pose(
offset: Pose,
) → Pose
compute_local_pose(
world_pose: Pose,
) → Pose
contiguous() → Pose
_abc_impl = <_abc._abc_data object>
_is_protocol = False
count(
value,
) → integer -- return number of occurrences of value
index(
value[,
start[,
stop,]]
) → integer -- return first index of value.

Raises ValueError if the value is not present.

Supporting start and stop arguments is optional, but recommended.

quat_multiply(q1, q2, q_res)
angular_distance_phi3(
goal_quat,
current_quat,
)

This function computes the angular distance phi_3.

See Huynh, Du Q. “Metrics for 3D rotations: Comparison and analysis.” Journal of Mathematical Imaging and Vision 35 (2009): 155-164.

Parameters:

  • goal_quat – _description_

  • current_quat – _description_

Returns:

Angular distance in range [0,1]

class OrientationError(*args, **kwargs)

Bases: Function

static geodesic_distance(
goal_quat,
current_quat,
quat_res,
)
static forward(
ctx,
goal_quat,
current_quat,
quat_res,
)

This function is to be overridden by all subclasses. There are two ways to define forward:

Usage 1 (Combined forward and ctx):

@staticmethod
def forward(ctx: Any, *args: Any, **kwargs: Any) -> Any:
    pass

Usage 2 (Separate forward and ctx):

@staticmethod
def forward(*args: Any, **kwargs: Any) -> Any:
    pass

@staticmethod
def setup_context(ctx: Any, inputs: Tuple[Any, ...], output: Any) -> None:
    pass

  • The forward no longer accepts a ctx argument.

  • Instead, you must also override the torch.autograd.Function.setup_context staticmethod to handle setting up the ctx object. output is the output of the forward, inputs are a Tuple of inputs to the forward.

  • See Extending torch.autograd for more details

The context can be used to store arbitrary data that can be then retrieved during the backward pass. Tensors should not be stored directly on ctx (though this is not currently enforced for backward compatibility). Instead, tensors should be saved either with ctx.save_for_backward if they are intended to be used in backward (equivalently, vjp) or ctx.save_for_forward if they are intended to be used for in jvp.

static backward(ctx, grad_out)

Defines a formula for differentiating the operation with backward mode automatic differentiation (alias to the vjp function).

This function is to be overridden by all subclasses.

It must accept a context ctx as the first argument, followed by as many outputs as the forward returned (None will be passed in for non tensor outputs of the forward function), and it should return as many tensors, as there were inputs to forward. Each argument is the gradient w.r.t the given output, and each returned value should be the gradient w.r.t. the corresponding input. If an input is not a Tensor or is a Tensor not requiring grads, you can just pass None as a gradient for that input.

The context can be used to retrieve tensors saved during the forward pass. It also has an attribute ctx.needs_input_grad as a tuple of booleans representing whether each input needs gradient. E.g., backward will have ctx.needs_input_grad[0] = True if the first input to forward needs gradient computed w.r.t. the output.

_backward_cls

alias of OrientationErrorBackward

_get_compiled_autograd_symints()
_is_compiled_autograd_tracing()
_materialize_non_diff_grads
_raw_saved_tensors
static _register_hook(
backward_hooks,
hook,
)
_register_hook_dict()
_sequence_nr()
classmethod apply(*args, **kwargs)
dirty_tensors
generate_vmap_rule = False
is_traceable = False

Bool that specifies if PyTorch should attempt to autogenerate torch.vmap support for this autograd.Function. You may set this to True only if this autograd.Function’s forward, backward, and jvp (if they exist) are written using PyTorch operations; otherwise, please override torch.autograd.Function.vmap to add support for torch.vmap.

Please see Extending torch.func with autograd.Function for more details.

static jvp(
ctx: Any,
*grad_inputs: Any,
) → Any

Defines a formula for differentiating the operation with forward mode automatic differentiation. This function is to be overridden by all subclasses. It must accept a context ctx as the first argument, followed by as many inputs as the forward got (None will be passed in for non tensor inputs of the forward function), and it should return as many tensors as there were outputs to forward. Each argument is the gradient w.r.t the given input, and each returned value should be the gradient w.r.t. the corresponding output. If an output is not a Tensor or the function is not differentiable with respect to that output, you can just pass None as a gradient for that input.

You can use the ctx object to pass any value from the forward to this functions.

mark_dirty(
*args: Tensor,
)

Marks given tensors as modified in an in-place operation.

This should be called at most once, only from inside the forward method, and all arguments should be inputs.

Every tensor that’s been modified in-place in a call to forward should be given to this function, to ensure correctness of our checks. It doesn’t matter whether the function is called before or after modification.

Examples::
>>> # xdoctest: +REQUIRES(env:TORCH_DOCTEST_AUTOGRAD)
>>> class Inplace(Function):
>>>     @staticmethod
>>>     def forward(ctx, x):
>>>         x_npy = x.numpy() # x_npy shares storage with x
>>>         x_npy += 1
>>>         ctx.mark_dirty(x)
>>>         return x
>>>
>>>     @staticmethod
>>>     @once_differentiable
>>>     def backward(ctx, grad_output):
>>>         return grad_output
>>>
>>> a = torch.tensor(1., requires_grad=True, dtype=torch.double).clone()
>>> b = a * a
>>> Inplace.apply(a)  # This would lead to wrong gradients!
>>>                   # but the engine would not know unless we mark_dirty
>>> # xdoctest: +SKIP
>>> b.backward() # RuntimeError: one of the variables needed for gradient
>>>              # computation has been modified by an inplace operation
mark_non_differentiable(
*args: Tensor,
)

Marks outputs as non-differentiable.

This should be called at most once, only from inside the forward method, and all arguments should be tensor outputs.

This will mark outputs as not requiring gradients, increasing the efficiency of backward computation. You still need to accept a gradient for each output in backward, but it’s always going to be a zero tensor with the same shape as the shape of a corresponding output.

This is used e.g. for indices returned from a sort. See example::
>>> class Func(Function):
>>>     @staticmethod
>>>     def forward(ctx, x):
>>>         sorted, idx = x.sort()
>>>         ctx.mark_non_differentiable(idx)
>>>         ctx.save_for_backward(x, idx)
>>>         return sorted, idx
>>>
>>>     @staticmethod
>>>     @once_differentiable
>>>     def backward(ctx, g1, g2):  # still need to accept g2
>>>         x, idx = ctx.saved_tensors
>>>         grad_input = torch.zeros_like(x)
>>>         grad_input.index_add_(0, idx, g1)
>>>         return grad_input
mark_shared_storage(
*pairs,
)
materialize_grads
maybe_clear_saved_tensors()
metadata
name()
needs_input_grad
next_functions
non_differentiable
register_hook()
register_prehook()
requires_grad
save_for_backward(
*tensors: Tensor,
)

Saves given tensors for a future call to backward.

save_for_backward should be called at most once, only from inside the forward method, and only with tensors.

All tensors intended to be used in the backward pass should be saved with save_for_backward (as opposed to directly on ctx) to prevent incorrect gradients and memory leaks, and enable the application of saved tensor hooks. See torch.autograd.graph.saved_tensors_hooks.

Note that if intermediary tensors, tensors that are neither inputs nor outputs of forward, are saved for backward, your custom Function may not support double backward. Custom Functions that do not support double backward should decorate their backward method with @once_differentiable so that performing double backward raises an error. If you’d like to support double backward, you can either recompute intermediaries based on the inputs during backward or return the intermediaries as the outputs of the custom Function. See the double backward tutorial for more details.

In backward, saved tensors can be accessed through the saved_tensors attribute. Before returning them to the user, a check is made to ensure they weren’t used in any in-place operation that modified their content.

Arguments can also be None. This is a no-op.

See Extending torch.autograd for more details on how to use this method.

Example::
>>> # xdoctest: +REQUIRES(env:TORCH_DOCTEST_AUTOGRAD)
>>> class Func(Function):
>>>     @staticmethod
>>>     def forward(ctx, x: torch.Tensor, y: torch.Tensor, z: int):
>>>         w = x * z
>>>         out = x * y + y * z + w * y
>>>         ctx.save_for_backward(x, y, w, out)
>>>         ctx.z = z  # z is not a tensor
>>>         return out
>>>
>>>     @staticmethod
>>>     @once_differentiable
>>>     def backward(ctx, grad_out):
>>>         x, y, w, out = ctx.saved_tensors
>>>         z = ctx.z
>>>         gx = grad_out * (y + y * z)
>>>         gy = grad_out * (x + z + w)
>>>         gz = None
>>>         return gx, gy, gz
>>>
>>> a = torch.tensor(1., requires_grad=True, dtype=torch.double)
>>> b = torch.tensor(2., requires_grad=True, dtype=torch.double)
>>> c = 4
>>> d = Func.apply(a, b, c)
save_for_forward(
*tensors: Tensor,
)

Saves given tensors for a future call to jvp.

save_for_forward should be only called once, from inside the forward method, and only be called with tensors.

In jvp, saved objects can be accessed through the saved_tensors attribute.

Arguments can also be None. This is a no-op.

See Extending torch.autograd for more details on how to use this method.

Example::
>>> # xdoctest: +SKIP
>>> class Func(torch.autograd.Function):
>>>     @staticmethod
>>>     def forward(ctx, x: torch.Tensor, y: torch.Tensor, z: int):
>>>         ctx.save_for_backward(x, y)
>>>         ctx.save_for_forward(x, y)
>>>         ctx.z = z
>>>         return x * y * z
>>>
>>>     @staticmethod
>>>     def jvp(ctx, x_t, y_t, _):
>>>         x, y = ctx.saved_tensors
>>>         z = ctx.z
>>>         return z * (y * x_t + x * y_t)
>>>
>>>     @staticmethod
>>>     def vjp(ctx, grad_out):
>>>         x, y = ctx.saved_tensors
>>>         z = ctx.z
>>>         return z * grad_out * y, z * grad_out * x, None
>>>
>>>     a = torch.tensor(1., requires_grad=True, dtype=torch.double)
>>>     t = torch.tensor(1., dtype=torch.double)
>>>     b = torch.tensor(2., requires_grad=True, dtype=torch.double)
>>>     c = 4
>>>
>>>     with fwAD.dual_level():
>>>         a_dual = fwAD.make_dual(a, t)
>>>         d = Func.apply(a_dual, b, c)
saved_for_forward
saved_tensors
saved_variables
set_materialize_grads(
value: bool,
)

Sets whether to materialize grad tensors. Default is True.

This should be called only from inside the forward method

If True, undefined grad tensors will be expanded to tensors full of zeros prior to calling the backward and jvp methods.

Example::
>>> # xdoctest: +REQUIRES(env:TORCH_DOCTEST_AUTOGRAD)
>>> class SimpleFunc(Function):
>>>     @staticmethod
>>>     def forward(ctx, x):
>>>         return x.clone(), x.clone()
>>>
>>>     @staticmethod
>>>     @once_differentiable
>>>     def backward(ctx, g1, g2):
>>>         return g1 + g2  # No check for None necessary
>>>
>>> # We modify SimpleFunc to handle non-materialized grad outputs
>>> class Func(Function):
>>>     @staticmethod
>>>     def forward(ctx, x):
>>>         ctx.set_materialize_grads(False)
>>>         ctx.save_for_backward(x)
>>>         return x.clone(), x.clone()
>>>
>>>     @staticmethod
>>>     @once_differentiable
>>>     def backward(ctx, g1, g2):
>>>         x, = ctx.saved_tensors
>>>         grad_input = torch.zeros_like(x)
>>>         if g1 is not None:  # We must check for None now
>>>             grad_input += g1
>>>         if g2 is not None:
>>>             grad_input += g2
>>>         return grad_input
>>>
>>> a = torch.tensor(1., requires_grad=True)
>>> b, _ = Func.apply(a)  # induces g2 to be undefined
static setup_context(
ctx: Any,
inputs: Tuple[Any, ...],
output: Any,
) → Any

There are two ways to define the forward pass of an autograd.Function.

Either:

  1. Override forward with the signature forward(ctx, *args, **kwargs). setup_context is not overridden. Setting up the ctx for backward happens inside the forward.

  2. Override forward with the signature forward(*args, **kwargs) and override setup_context. Setting up the ctx for backward happens inside setup_context (as opposed to inside the forward)

See torch.autograd.Function.forward and Extending torch.autograd for more details.

to_save
static vjp(
ctx: Any,
*grad_outputs: Any,
) → Any

Defines a formula for differentiating the operation with backward mode automatic differentiation (alias to the vjp function).

This function is to be overridden by all subclasses.

It must accept a context ctx as the first argument, followed by as many outputs as the forward returned (None will be passed in for non tensor outputs of the forward function), and it should return as many tensors, as there were inputs to forward. Each argument is the gradient w.r.t the given output, and each returned value should be the gradient w.r.t. the corresponding input. If an input is not a Tensor or is a Tensor not requiring grads, you can just pass None as a gradient for that input.

The context can be used to retrieve tensors saved during the forward pass. It also has an attribute ctx.needs_input_grad as a tuple of booleans representing whether each input needs gradient. E.g., backward will have ctx.needs_input_grad[0] = True if the first input to forward needs gradient computed w.r.t. the output.

static vmap(
info,
in_dims,
*args,
)

Defines a rule for the behavior of this autograd.Function underneath torch.vmap. For a torch.autograd.Function to support torch.vmap, you must either override this staticmethod, or set generate_vmap_rule to True (you may not do both).

If you choose to override this staticmethod: it must accept

  • an info object as the first argument. info.batch_size specifies the size of the dimension being vmapped over, while info.randomness is the randomness option passed to torch.vmap.

  • an in_dims tuple as the second argument. For each arg in args, in_dims has a corresponding Optional[int]. It is None if the arg is not a Tensor or if the arg is not being vmapped over, otherwise, it is an integer specifying what dimension of the Tensor is being vmapped over.

  • *args, which is the same as the args to forward.

The return of the vmap staticmethod is a tuple of (output, out_dims). Similar to in_dims, out_dims should be of the same structure as output and contain one out_dim per output that specifies if the output has the vmapped dimension and what index it is in.

Please see Extending torch.func with autograd.Function for more details.

normalize_quaternion(
in_quaternion: Tensor,
) → Tensor