robocasa.models.objects package#

Submodules#

robocasa.models.objects.kitchen_objects module#

class robocasa.models.objects.kitchen_objects.ObjCat(name, types, model_folders=None, exclude=None, graspable=False, washable=False, microwavable=False, cookable=False, freezable=False, scale=1.0, solimp=(0.998, 0.998, 0.001), solref=(0.001, 2), density=100, friction=(0.95, 0.3, 0.1), priority=None, aigen_cat=False)#

Bases: object

Class that encapsulates data for an object category.

Parameters

  • name (str) – name of the object category

  • types (tuple) or (str) – type(s)/categories the object belongs to. Examples include meat, sweets, fruit, etc.

  • model_folders (list) – list of folders containing the MJCF models for the object category

  • exclude (list) – list of model names to exclude

  • graspable (bool) – whether the object is graspable

  • washable (bool) – whether the object is washable

  • microwavable (bool) – whether the object is microwavable

  • cookable (bool) – whether the object is cookable

  • freezable (bool) – whether the object is freezable

  • scale (float) – scale of the object meshes/geoms

  • solimp (tuple) – solimp values for the object meshes/geoms

  • solref (tuple) – solref values for the object meshes/geoms

  • density (float) – density of the object meshes/geoms

  • friction (tuple) – friction values for the object meshes/geoms

  • priority – priority of the object

  • aigen_cat (bool) – True if the object is an AI-generated object otherwise its an objaverse object

get_mjcf_kwargs()#

returns relevant data to apply to the MJCF model for the object category

robocasa.models.objects.kitchen_objects.sample_kitchen_object(groups, exclude_groups=None, graspable=None, washable=None, microwavable=None, cookable=None, freezable=None, rng=None, obj_registries=('objaverse',), split=None, max_size=(None, None, None), object_scale=None)#

Sample a kitchen object from the specified groups and within max_size bounds.

Parameters

  • groups (list or str) – groups to sample from or the exact xml path of the object to spawn

  • exclude_groups (str or list) – groups to exclude

  • graspable (bool) – whether the sampled object must be graspable

  • washable (bool) – whether the sampled object must be washable

  • microwavable (bool) – whether the sampled object must be microwavable

  • cookable (bool) – whether whether the sampled object must be cookable

  • freezable (bool) – whether whether the sampled object must be freezable

  • rng (np.random.Generator) – random number object

  • obj_registries (tuple) – registries to sample from

  • split (str) – split to sample from. Split “A” specifies all but the last 3 object instances (or the first half - whichever is larger), “B” specifies the rest, and None specifies all.

  • max_size (tuple) – max size of the object. If the sampled object is not within bounds of max size, function will resample

  • object_scale (float) – scale of the object. If set will multiply the scale of the sampled object by this value

Returns

kwargs to apply to the MJCF model for the sampled object

dict: info about the sampled object - the path of the mjcf, groups which the object’s category belongs to, the category of the object

the sampling split the object came from, and the groups the object was sampled from

Return type

dict

robocasa.models.objects.kitchen_objects.sample_kitchen_object_helper(groups, exclude_groups=None, graspable=None, washable=None, microwavable=None, cookable=None, freezable=None, rng=None, obj_registries=('objaverse',), split=None, object_scale=None)#

Helper function to sample a kitchen object.

Parameters

  • groups (list or str) – groups to sample from or the exact xml path of the object to spawn

  • exclude_groups (str or list) – groups to exclude

  • graspable (bool) – whether the sampled object must be graspable

  • washable (bool) – whether the sampled object must be washable

  • microwavable (bool) – whether the sampled object must be microwavable

  • cookable (bool) – whether whether the sampled object must be cookable

  • freezable (bool) – whether whether the sampled object must be freezable

  • rng (np.random.Generator) – random number object

  • obj_registries (tuple) – registries to sample from

  • split (str) – split to sample from. Split “A” specifies all but the last 3 object instances (or the first half - whichever is larger), “B” specifies the rest, and None specifies all.

  • object_scale (float) – scale of the object. If set will multiply the scale of the sampled object by this value

Returns

kwargs to apply to the MJCF model for the sampled object

dict: info about the sampled object - the path of the mjcf, groups which the object’s category belongs to, the category of the object

the sampling split the object came from, and the groups the object was sampled from

Return type

dict

robocasa.models.objects.objects module#

class robocasa.models.objects.objects.MJCFObject(name, mjcf_path, scale=1.0, solimp=(0.998, 0.998, 0.001), solref=(0.001, 1), density=100, friction=(0.95, 0.3, 0.1), margin=None, rgba=None, priority=None)#

Bases: robosuite.models.objects.objects.MujocoXMLObject

Blender object with support for changing the scaling

get_bbox_points(trans=None, rot=None)#

Get the full 8 bounding box points of the object rot: a rotation matrix

property horizontal_radius#

Returns maximum distance from model root body to any radial point of the model.

Helps us put models programmatically without them flying away due to a huge initial contact force. Must be defined by subclass.

Returns

radius

Return type

float

postprocess_model_xml(xml_str)#

New version of postprocess model xml that only replaces robosuite file paths if necessary (otherwise there is an error with the “max” operation)

Module contents#