6D-Platform MagBot#

../_images/img_6DPlatformMagBot_sim2real.png
class magbotsim.magbots.sixD_platform.SixDPlatformMagBotsAPM4330(num_magbots: int, indices_mover_a: ndarray, indices_mover_b: ndarray)[source]

Bases: object

Base class for 6D-Platform MagBots. This class can handle multiple 6D-Platform MagBots, allowing calculations to be vectorized.

Parameters:

  • num_magbots – number of 6D-Platform MagBots

  • indices_mover_a – a numpy array of shape (num_magbots,) containing all indices of movers controlling the alpha-rotation (around x-axis) of a platform

  • indices_mover_b – a numpy array of shape (num_magbots,) containing all indices of movers controlling the beta-rotation (around y-axis) of a platform

control_platform_ab_rot(model: MjModel, data: MjData, mover_a_quats: ndarray, mover_b_quats: ndarray, indices_magbots: ndarray | None = None) → None[source]

Couple the rotations around the z-axes of the movers with the platform’s a and b rotations. This method is vectorized and can therefore couple the rotations for multiple MagBots.

Parameters:

  • model – mjModel of the MuJoCo environment

  • data – mjData of the MuJoCo environment

  • mover_a_quats – current rotations of the movers (represented as quaternions (w,x,y,z)) that control the platform’s alpha-rotation. Shape: (num_indices, 4)

  • mover_b_quats – current rotations of the movers (represented as quaternions (w,x,y,z)) that control the platform’s beta-rotation. Shape: (num_indices, 4)

  • indices_magbots – the indices of the MagBots to control, defaults to None. If None, all MagBots are controlled. Shape: (num_indices,)

generate_magbot_xml_strings(initial_pos_xyz_mover_b: ndarray, custom_model_xml_strings: dict | None) → dict[source]

Generate the MuJoCo XML strings for all 6D-Platform MagBots and add them to the custom_model_xml_strings-dict.

Parameters:

  • initial_pos_xyz_mover_b – the initial x,y,z-positions for all movers that control the b rotation of the platforms. Shape: (num_magbots,3)

  • custom_model_xml_strings – the current custom_model_xml_strings-dict which is modified by this method

Returns:

the modified custom_model_xml_strings-dict

generate_platform_abRot_actuator_xml_strings() → str[source]

Generate MuJoCo XML strings for the a,b-rot platform actuators of all 6D-Platform MagBots.

Returns:

the MuJoCo XML actuator string (start <actuator> and end ‘</actuator>’ are not included)

get_platform_acc(model: MjModel, data: MjData, idx_magbot: int) → ndarray[source]

Get the current acceleration of a MagBot’s platform (measured at the center of the platform’s surface).

Parameters:

  • model – mjModel of the MuJoCo environment

  • data – mjData of the MuJoCo environment

  • idx_magbot – the index of the MagBot for which to return the acceleration

Returns:

the current acceleration of the platform. Shape: (6,) (first 3: linear accelerations, last 3: angular accelerations)

get_platform_pose(model: MjModel, data: MjData, indices_magbots: ndarray) → ndarray[source]

Get the current pose of a MagBot’s platform (measured at the center of the platform’s surface). This method is vectorized and can therefore calculate the current pose of multiple MagBots.

Parameters:

  • model – mjModel of the MuJoCo environment

  • data – mjData of the MuJoCo environment

  • indices_magbots – the indices of the MagBots for which to return the pose. Shape: (num_indices,)

Returns:

the current pose of the platforms (rotation represented as quaternion). Shape: (num_indices,7) (representation: (x_p,y_p,z_p,w_o,x_o,y_o,z_o))

get_platform_vel(model: MjModel, data: MjData, idx_magbot: int) → ndarray[source]

Get the current velocity of a MagBot’s platform (measured at the center of the platform’s surface).

Parameters:

  • model – mjModel of the MuJoCo environment

  • data – mjData of the MuJoCo environment

  • idx_magbot – the index of the MagBot for which to return the velocity

Returns:

the current velocity of the platform. Shape: (6,) (first 3: linear velocities, last 3: angular velocities)

platformSetPose2MoverSetPose(platform_pose_d: ndarray, mover_z_d: ndarray | float, use_euler: bool = False) → ndarray[source]

Calculate the desired mover pose from a desired platform pose. This method is vectorized and can therefore calculate desired mover poses for multiple MagBots.

Parameters:

  • platform_pose_d – the desired platform poses (rotation specified as Euler angles (xyz) in rad). Shape: (num_samples,6)

  • mover_z_d – the desired mover z-pos (corresponds to the distance between the tile surface and the bottom of a mover). Can be a numpy array of shape (num_samples,) or a single float value (similar position for all movers).

  • use_euler – whether to use quaternions (w,x,y,z) or euler angles (xyz) to represent the desired mover rotations, defaults to False

Returns:

the desired mover poses. Shape: if use_euler==True: (num_samples,2,6), else: (num_samples,2,7). [:,0,:]: poses for the mover that controls the platform’s alpha-rotation; [:,1,:]: poses for the mover that controls the platform’s beta-rotation

platformZPos2MoverDist(platform_z_d: ndarray, mover_z_d: ndarray) → ndarray[source]

Calculate the desired mover distance from a desired platform z-position. This method is vectorized and can therefore calculate desired mover distances for multiple MagBots. Additionally this method takes the minimum and maximum possible mover distances into account, i.e. distances that are less (greater) than the minimum (maximum) distance are set to the minimum (maximum) distance.

Parameters:

  • platform_z_d – the desired platform z-positions. Shape: (num_samples,) or (num_samples,1)

  • mover_z_d – the desired mover z-pos (corresponds to the distance between the tile surface and the bottom of a mover). Shape: (num_samples,) or (num_samples,1)

Returns:

the desired mover distances. Shape: (num_samples,) or (num_samples,1) depending on the input shapes

update_cached_mujoco_data(model: MjModel) → None[source]

Update all cached information about MuJoCo objects, such as names and IDs.

Parameters:

model – mjModel of the MuJoCo environment