tbp.monty.frameworks.models.salience

tbp.monty.frameworks.models.salience.on_object_observation

class OnObjectObservation(center_location: np.ndarray | None, locations: np.ndarray, salience: np.ndarray) → None

Bases: object

__init__(center_location: np.ndarray | None, locations: np.ndarray, salience: np.ndarray) → None

center_location: np.ndarray | None

locations: np.ndarray

salience: np.ndarray

on_object_observation(raw_observation: dict, salience_map: numpy.ndarray) → OnObjectObservation

Convert all raw observation data into image format.

This function reformats the arrays in a raw observations dictionary so that they’re all indexable by image row and column indices. It also splits the semantic_3d array into 3D locations and an on-object/surface indicator array.

Parameters:

• raw_observation (dict) – A sensor’s raw observations dictionary.

• salience_map (ndarray) – A salience map.

Return type:

OnObjectObservation

Returns:

The grid/matrix formatted (unraveled) on-object salience and location data, along with the location corresponding to the central pixel.

tbp.monty.frameworks.models.salience.return_inhibitor

class DecayField(kernel_factory_class: type[DecayKernelFactory] = <class 'tbp.monty.frameworks.models.salience.return_inhibitor.DecayKernelFactory'>, kernel_factory_args: dict[str, Any] | None = None)

Bases: object

Manages a collection of decay kernels.

__init__(kernel_factory_class=<class 'tbp.monty.frameworks.models.salience.return_inhibitor.DecayKernelFactory'>, kernel_factory_args=None)

add(location: numpy.ndarray) → None

Add a kernel to the field.

Return type:

None

compute_weights(points: numpy.ndarray) → numpy.ndarray

Return type:

ndarray

reset() → None

Return type:

None

step() → None

Step each kernel to increment its counter, and keep only non-expired ones.

Return type:

None

class DecayKernel(location: np.ndarray, tau_t: float = 10.0, tau_s: float = 0.01, spatial_cutoff: float | None = 0.02, w_t_min: float = 0.1)

Bases: object

Decay kernel represents a previously visited location.

Returns the product of an time- and space- dependent exponentials.

__init__(location: np.ndarray, tau_t: float = 10.0, tau_s: float = 0.01, spatial_cutoff: float | None = 0.02, w_t_min: float = 0.1)

step() → bool

Increment the step counter, and check if the kernel is expired.

Return type:

bool

Returns:

True if the kernel is expired, False otherwise.

w_s(points: numpy.ndarray) → numpy.ndarray

Compute the distance-dependent weight.

The weight is computed as exp(-z / lam), where z is the distance between the kernel’s center and the given point(s), and lam is equal to tau_s / log(2).

Parameters:

points (ndarray) – An (num_points, 3) array of points.

Return type:

ndarray

Returns:

The weight, bounded to [0, 1]. Has shape (num_points,).

w_t() → float

Compute the time-dependent weight at the current step.

The weight is computed as exp(-t / lam), where t is the number of steps since the kernel was created, and lam is equal to tau_t / log(2).

Return type:

float

Returns:

The weight, bounded to [0, 1].

class DecayKernelFactory(tau_t: float = 10.0, tau_s: float = 0.01, spatial_cutoff: float | None = 0.02, w_t_min: float = 0.1)

Bases: object

__init__(tau_t: float = 10.0, tau_s: float = 0.01, spatial_cutoff: float | None = 0.02, w_t_min: float = 0.1)

class ReturnInhibitor(decay_field_class: type[DecayField] = <class 'tbp.monty.frameworks.models.salience.return_inhibitor.DecayField'>, decay_field_args: dict[str, Any] | None = None)

Bases: object

__init__(decay_field_class=<class 'tbp.monty.frameworks.models.salience.return_inhibitor.DecayField'>, decay_field_args=None)

reset() → None

Return type:

None

tbp.monty.frameworks.models.salience.sensor_module

class HabitatSalienceSM(rng, sensor_module_id: str, save_raw_obs: bool = False, salience_strategy_class: type[SalienceStrategy] = <class 'tbp.monty.frameworks.models.salience.strategies.UniformSalienceStrategy'>, salience_strategy_args: dict[str, Any] | None = None, return_inhibitor_class: type[ReturnInhibitor] = <class 'tbp.monty.frameworks.models.salience.return_inhibitor.ReturnInhibitor'>, return_inhibitor_args: dict[str, Any] | None = None, snapshot_telemetry_class: type[SnapshotTelemetry] = <class 'tbp.monty.frameworks.models.sensor_modules.SnapshotTelemetry'>) → None

Bases: SensorModule

__init__(rng, sensor_module_id, save_raw_obs=False, salience_strategy_class=<class 'tbp.monty.frameworks.models.salience.strategies.UniformSalienceStrategy'>, salience_strategy_args=None, return_inhibitor_class=<class 'tbp.monty.frameworks.models.salience.return_inhibitor.ReturnInhibitor'>, return_inhibitor_args=None, snapshot_telemetry_class=<class 'tbp.monty.frameworks.models.sensor_modules.SnapshotTelemetry'>)

pre_episode()

This method is called before each episode.

propose_goal_states() → list[GoalState]

Return the goal-states proposed by this Sensor Module.

state_dict()

Return a serializable dict with this sensor module’s state.

Includes everything needed to save/load this sensor module.

step(data) → State | None

Generate goal states for the current step.

Parameters:

data – Raw sensor observations

Return type:

State | None

Returns:

A Percept, if one is generated.

update_state(state)

Update the state of the sensor module.

tbp.monty.frameworks.models.salience.strategies

class SalienceStrategy(*args, **kwargs)

Bases: Protocol

__init__(*args, **kwargs)

class UniformSalienceStrategy(*args, **kwargs)

Bases: SalienceStrategy