float : The mass of the mesh (read-only).

**Input:** - numpy array of shape (3, 3) of the rotation matrix. **Output:** - binormal: numpy array of shape (3,). - angle:

Combines this mesh with another mesh. Parameters ---------- other_mesh : :obj:`Mesh3D` the mesh to combine with

Min singular value of grasp matrix - measure of wrench that grasp is "weakest" at resisting. Parameters ---------- forces :

:obj:`numpy.ndarray` of float : A #normals by 3 array, where each row contains a normalized vector. This list should contain one norm

:obj:`int`: The number of total triangles

:obj:`int`: The number of total vertices

**Output:** - int of the object id that this grasp grasps

**Output:** - int of the object id that this grasp grasps

**Output:** - numpy array of shape (-1, ) of the object ids.

**Output:** - numpy array of the object ids that this grasp grasps.

**Output:** - tuple of x,y of the open point.

**Output:** - numpy array the open points of shape (-1, 2).

float : maximum opening width of the jaws

The location of the origin in the SDF grid. Returns ------- :obj:`numpy.ndarray` of float The 2- or 3-ndarray tha

Returns a grasp with approach_angle set to be perpendicular to the table normal specified in the given stable pose. Parameters

Converts configuration vector into grasp parameters. Returns ------- grasp_center : :obj:`numpy.ndarray` center o

Converts configuration vector into vacuum grasp parameters. Returns ------- center : :obj:`numpy.ndarray` center

**Input:** - posevector: list of pose **Output:** - obj_idx: int of the index of object. - mat: numpy array of shape (4, 4) of th

Evalutes partial closure: whether or not the forces and torques can resist a specific wrench. Estimates resistance by sollving a quadratic

Returns a grasp with approach_angle set to be aligned width the table normal specified in the given stable pose. Parameters -

Project a grasp for a given gripper into the camera specified by a set of intrinsics. Parameters ---------- T_obj_cam

Compute grasp quality using a quasistatic method. Parameters ---------- grasp : :obj:`GraspableObject3D` grasp to

Compute grasp quality using a robust quasistatic method. Parameters ---------- grasp : :obj:`GraspableObject3D` g

Generate uniformly random points on the surface of the mesh. Parameters ---------- n_points : int The number of r

**Input:** - numGrasp: int of the number of sampled grasps. **Output:** - RectGraspGroup instance of sample grasps

Returns a list containing the indices of the triangles that are intersected by the given ray emanating from the given point within some

Returns the local reference frame of the contact. Z axis in the in direction (or surface normal if not specified) X and Y axes in the

**Input:** - index: list of the index of rect_grasp

Remove triangles with out-of-bounds vertices from the mesh.

Rescales uniformly by a given factor. Parameters ---------- scale : float the amount to scale the object

Rescale an SDF by a given scale factor. Parameters ---------- scale : float the amount to scale the SDF

Rescales the vertex coordinates by scale_factor. Parameters ---------- scale_factor : float The desired scale fac

Rescales the vertex coordinates to scale using the given scaling_type. Parameters ---------- scale : float

return a ResNet 101 object.

return a ResNet 152 object.

return a ResNet 18 object.

return a ResNet 34 object.

return a ResNet 50 object.

The grid resolution (how wide each grid cell is). Returns ------- float The width of each grid cell.

Returns the stable pose that the mesh will rest on if it lands on an infinite planar worksurface quasi-statically in the given transfo

Rotation matrix from canonical grasp reference frame to object reference frame. X axis points out of the gripper palm along the grasp

**Output:** - np.array of shape (-1, 3, 3) of the rotation matrices.

Author: chenxi-wang **Input:** - rx/ry/rz: float, rotation angle along x/y/z-axis **Output:** - numpy array of (3, 3), rotati

**Input:** - alpha: float of alpha angle. - beta: float of beta angle. - gamma: float of the gamma angle. **Output:** -

**Output:** - np.array of shape (3, 3) of the rotation matrix.

**Input:** - npy_file_path: string of the file path.

**Output:** - float of the score.

**Output:** - float of the score.

**Output:** - numpy array of shape (-1, ) of the scores.

**Output:** - numpy array of the scores.

**Input:** - sceneIds: int or list of scene ids. - saveFolder: string of the folder to store the image. - show: bo

**Input:** - objIds: int of list of objects ids. - numGrasp: how many grasps to show in the image. - th: threshold

**Input:** - sceneId: int of the scene index. - camera: string of the camera type, 'realsense' or 'kinect'. - annI

**Input:** - reverse: bool of order, if False, from high to low, if True, from low to high. **Output:** - no outpu

Computes all valid StablePose objects for the mesh. Parameters ---------- min_prob : float stable poses that are

Return a copy of the mesh that has been subdivided by one iteration. Note ---- This method only copies the vertices and trian

Returns the support function in the given direction. Parameters ---------- direction : :obj:`numpy.ndarray` of float

Return the surface area of the mesh. Returns ------- float The surface area of the mesh.

Return the patch surface information at the contacts that this grasp makes on a graspable. Parameters ---------- gras

Returns the patches on this object for a given grasp. Parameters ---------- grasp : :obj:`ParallelJawPtGrasp3D` g

Returns the local surface window, gradient, and curvature for a single contact. Parameters ---------- width : float

Projects the local surface onto the tangent plane at a contact point. Deprecated.

Returns a window of SDF values on the tangent plane at a contact point. Used for patch computation. Parameters ----------

**Input:** - camera: string of type of camera, 'kinect' or 'realsense'. - depths: numpy array of the depths image.

**Input:** - camera: string of type of camera, 'kinect' or 'realsense'. - depths: numpy array of the depths image.

**input:** - opencv_rgb: numpy array of opencv BGR format. - numGrasp: int of the number of grasp, 0 for all. **Ou

**Input:** - camera: string of type of camera, 'realsense' or 'kinect'. **Output:** - RectGraspGroup instance or N

**Input:** - grasps: (N, 17) - k: int **Output:** - topk_grasps: (k, 17)

**Input:** - T: np.array of shape (4, 4) **Output:** - Grasp instance after transformation, the original Grasp wil

**Input:** - T: np.array of shape (4, 4) **Output:** - GraspGroup instance after transformation, the original Gras

Creates a new SDF with a given pose with respect to world coordinates. Parameters ---------- delta_T : :obj:`autolab_

Transform the grid by pose T and scale with canonical reference frame at the SDF center with axis alignment. Parameters -----

Author: chenxi-wang **Input:** - tx/ty/tz: float, translation along x/y/z-axis - rx/ry/rz: float, rotation angle along x/y/z-axis

Converts a point in sdf coords to the grid basis. If direction then don't translate. Parameters ---------- x_sdf : nu

Returns an sdf object with center in the world frame of reference.

**Output:** - np.array of shape (3,) of the translation.

**Output:** - np.array of shape (-1, 3) of the translations.