adam.parametric.pytorch

adam.parametric.pytorch#

Submodules#

Classes#

KinDynComputationsParametric

This is a small class that retrieves robot quantities using Pytorch for Floating Base systems.

Package Contents#

class adam.parametric.pytorch.KinDynComputationsParametric(urdfstring: str, joints_name_list: list, links_name_list: list, root_link: str = None, gravity: numpy.array = torch.tensor([0, 0, -9.80665, 0, 0, 0]))[source]#

This is a small class that retrieves robot quantities using Pytorch for Floating Base systems. This is parametric w.r.t the link length and densities.

math#
g#
joints_name_list#
urdfstring#
representation#
set_frame_velocity_representation(representation: adam.core.constants.Representations) → None[source]#

Sets the representation of the velocity of the frames

Parameters:

representation (Representations) – The representation of the velocity

mass_matrix(base_transform: torch.Tensor, s: torch.Tensor, length_multiplier: torch.Tensor, densities: torch.Tensor) → torch.Tensor[source]#

Returns the Mass Matrix functions computed the CRBA

Parameters:

  • base_transform (torch.tensor) – The homogenous transform from base to world frame

  • s (torch.tensor) – The joints position

  • length_multiplier (torch.tensor) – The length multiplier of the parametrized links

  • densities (torch.tensor) – The densities of the parametrized links

Returns:

Mass Matrix

Return type:

M (torch.tensor)

centroidal_momentum_matrix(base_transform: torch.Tensor, s: torch.Tensor, length_multiplier: torch.Tensor, densities: torch.Tensor) → torch.Tensor[source]#

Returns the Centroidal Momentum Matrix functions computed the CRBA

Parameters:

  • base_transform (torch.tensor) – The homogenous transform from base to world frame

  • s (torch.tensor) – The joints position

  • length_multiplier (torch.tensor) – The length multiplier of the parametrized links

  • densities (torch.tensor) – The densities of the parametrized links

Returns:

Centroidal Momentum matrix

Return type:

Jcc (torch.tensor)

forward_kinematics(frame, base_transform: torch.Tensor, joint_positions: torch.Tensor, length_multiplier: torch.Tensor, densities: torch.Tensor) → torch.Tensor[source]#

Computes the forward kinematics relative to the specified frame

Parameters:

  • frame (str) – The frame to which the fk will be computed

  • base_transform (torch.tensor) – The homogenous transform from base to world frame

  • joint_positions (torch.tensor) – The joints position

  • length_multiplier (torch.tensor) – The length multiplier of the parametrized links

  • densities (torch.tensor) – The densities of the parametrized links

Returns:

The fk represented as Homogenous transformation matrix

Return type:

T_fk (torch.tensor)

jacobian(frame: str, base_transform: torch.Tensor, joint_positions: torch.Tensor, length_multiplier: torch.Tensor, densities: torch.Tensor) → torch.Tensor[source]#

Returns the Jacobian relative to the specified frame

Parameters:

  • frame (str) – The frame to which the jacobian will be computed

  • base_transform (torch.tensor) – The homogenous transform from base to world frame

  • joint_positions (torch.tensor) – The joints position

  • length_multiplier (torch.tensor) – The length multiplier of the parametrized links

  • densities (torch.tensor) – The densities of the parametrized links

Returns:

The Jacobian relative to the frame

Return type:

J_tot (torch.tensor)

relative_jacobian(frame, joint_positions: torch.Tensor, length_multiplier: torch.Tensor, densities: torch.Tensor) → torch.Tensor[source]#

Returns the Jacobian between the root link and a specified frame frames

Parameters:

  • frame (str) – The tip of the chain

  • joint_positions (torch.tensor) – The joints position

  • length_multiplier (torch.tensor) – The length multiplier of the parametrized links

  • densities (torch.tensor) – The densities of the parametrized links

Returns:

The Jacobian between the root and the frame

Return type:

J (torch.tensor)

jacobian_dot(frame: str, base_transform: torch.Tensor, joint_positions: torch.Tensor, base_velocity: torch.Tensor, joint_velocities: torch.Tensor, length_multiplier: torch.Tensor, densities: torch.Tensor) → torch.Tensor[source]#

Returns the Jacobian derivative relative to the specified frame

Parameters:

  • frame (str) – The frame to which the jacobian will be computed

  • base_transform (torch.Tensor) – The homogenous transform from base to world frame

  • joint_positions (torch.Tensor) – The joints position

  • base_velocity (torch.Tensor) – The base velocity

  • joint_velocities (torch.Tensor) – The joint velocities

  • length_multiplier (torch.tensor) – The length multiplier of the parametrized links

  • densities (torch.tensor) – The densities of the parametrized links

Returns:

The Jacobian derivative relative to the frame

Return type:

Jdot (torch.Tensor)

CoM_position(base_transform: torch.Tensor, joint_positions: torch.Tensor, length_multiplier: torch.Tensor, densities: torch.Tensor) → torch.Tensor[source]#

Returns the CoM position

Parameters:

  • base_transform (torch.tensor) – The homogenous transform from base to world frame

  • joint_positions (torch.tensor) – The joints position

  • length_multiplier (torch.tensor) – The length multiplier of the parametrized links

  • densities (torch.tensor) – The densities of the parametrized links

Returns:

The CoM position

Return type:

com (torch.tensor)

bias_force(base_transform: torch.Tensor, s: torch.Tensor, base_velocity: torch.Tensor, joint_velocities: torch.Tensor, length_multiplier: torch.Tensor, densities: torch.Tensor) → torch.Tensor[source]#

Returns the bias force of the floating-base dynamics ejoint_positionsuation, using a reduced RNEA (no acceleration and external forces)

Parameters:

  • base_transform (torch.tensor) – The homogenous transform from base to world frame

  • s (torch.tensor) – The joints position

  • base_velocity (torch.tensor) – The base velocity

  • joint_velocities (torch.tensor) – The joints velocity

  • length_multiplier (torch.tensor) – The length multiplier of the parametrized links

  • densities (torch.tensor) – The densities of the parametrized links

Returns:

the bias force

Return type:

h (torch.tensor)

coriolis_term(base_transform: torch.Tensor, joint_positions: torch.Tensor, base_velocity: torch.Tensor, joint_velocities: torch.Tensor, length_multiplier: torch.Tensor, densities: torch.Tensor) → torch.Tensor[source]#

Returns the coriolis term of the floating-base dynamics ejoint_positionsuation, using a reduced RNEA (no acceleration and external forces)

Parameters:

  • base_transform (torch.tensor) – The homogenous transform from base to world frame

  • joint_positions (torch.tensor) – The joints position

  • base_velocity (torch.tensor) – The base velocity

  • joint_velocities (torch.tensor) – The joints velocity

  • length_multiplier (torch.tensor) – The length multiplier of the parametrized links

  • densities (torch.tensor) – The densities of the parametrized links

Returns:

the Coriolis term

Return type:

C (torch.tensor)

gravity_term(base_transform: torch.Tensor, base_positions: torch.Tensor, length_multiplier: torch.Tensor, densities: torch.Tensor) → torch.Tensor[source]#

Returns the gravity term of the floating-base dynamics ejoint_positionsuation, using a reduced RNEA (no acceleration and external forces)

Parameters:

  • base_transform (torch.tensor) – The homogenous transform from base to world frame

  • base_positions (torch.tensor) – The joints position

  • length_multiplier (torch.tensor) – The length multiplier of the parametrized links

  • densities (torch.tensor) – The densities of the parametrized links

Returns:

the gravity term

Return type:

G (torch.tensor)

get_total_mass(length_multiplier: torch.Tensor, densities: torch.Tensor) → float[source]#

Returns the total mass of the robot

Parameters:

  • length_multiplier (torch.tensor) – The length multiplier of the parametrized links

  • densities (torch.tensor) – The densities of the parametrized links

Returns:

The total mass

Return type:

mass

get_original_densities() → list[float][source]#

Returns the original densities of the parametric links

Returns:

The original densities of the parametric links

Return type:

densities

Contents