CoverageEnvUtils Class Reference

Class for utility functions for coverage environment. More...

Static Public Member Functions
torch.Tensor	to_tensor (object data)
	Converts various types of data to torch.Tensor.
torch.Tensor	get_raw_local_maps (CoverageSystem env, Parameters params)
	Get raw local maps.
torch.Tensor	get_raw_obstacle_maps (CoverageSystem env, Parameters params)
	Get raw obstacle maps.
torch.Tensor	get_communication_maps (CoverageSystem env, Parameters params, int map_size)
	Generate communication maps from positions.
torch.Tensor	resize_maps (torch.Tensor maps, int resized_map_size)
	Resize maps to a given size Uses bilinear interpolation from torchvision.transforms.functional.resize Options antialias=True.
torch.Tensor	get_maps (CoverageSystem env, Parameters params, int resized_map_size, bool use_comm_map)
	Get maps for the coverage environment.
torch.Tensor	get_voronoi_features (CoverageSystem env)
	Get voronoi features.
torch.Tensor	get_robot_positions (CoverageSystem env)
	Get robot positions.
torch.Tensor	get_weights (CoverageSystem env, Parameters params)
	Get edge weights for the communication graph.
torch.Tensor	robot_positions_to_edge_weights (PointVector robot_positions, int world_map_size, float comm_range)
	Convert robot positions to edge weights.
torch_geometric.data.Data	get_torch_geometric_data (CoverageSystem env, Parameters params, bool use_cnn, bool use_comm_map, int map_size)
	Get torch geometric data In this function, the edge weights are binary.

Detailed Description

Class for utility functions for coverage environment.

Definition at line 46 of file coverage_env_utils.py.

Member Function Documentation

get_communication_maps()

torch.Tensor get_communication_maps ( CoverageSystem env, Parameters params, int map_size )

static

Generate communication maps from positions.

   Communication maps are composed of two channels.
   Each channnel has non-zero values for cells that correspond to the relative positions of the neighbors.
   For the first channel, the value is the x-coordinate of the relative position divided by the communication range.
   Similarly, the y-coordinte is used for the second channel.

Parameters

env	coverage environment
params	parameters
map_size	size of the map

Returns

torch communication maps

Definition at line 163 of file coverage_env_utils.py.

get_maps()

torch.Tensor get_maps ( CoverageSystem env, Parameters params, int resized_map_size, bool use_comm_map )

static

Get maps for the coverage environment.

Parameters

env	coverage environment
params	parameters
resized_map_size	size of the resized maps
use_comm_map	whether to use communication maps

Returns

torch maps

Definition at line 244 of file coverage_env_utils.py.

get_raw_local_maps()

torch.Tensor get_raw_local_maps ( CoverageSystem env, Parameters params )

static

Get raw local maps.

Parameters

env	coverage environment
params	parameters

Returns

torch raw local maps

Definition at line 112 of file coverage_env_utils.py.

get_raw_obstacle_maps()

torch.Tensor get_raw_obstacle_maps ( CoverageSystem env, Parameters params )

static

Get raw obstacle maps.

Parameters

env	coverage environment
params	parameters

Returns

torch raw obstacle maps

Definition at line 134 of file coverage_env_utils.py.

get_robot_positions()

torch.Tensor get_robot_positions ( CoverageSystem env )

static

Get robot positions.

Parameters

env	coverage environment

Returns

torch robot positions

Definition at line 309 of file coverage_env_utils.py.

get_torch_geometric_data()

torch_geometric.data.Data get_torch_geometric_data ( CoverageSystem env, Parameters params, bool use_cnn, bool use_comm_map, int map_size )

static

Get torch geometric data In this function, the edge weights are binary.

Parameters

env	coverage environment
params	parameters
use_cnn	whether to use CNN
use_comm_map	whether to use communication maps
map_size	size of the maps

Returns

torch_geometric torch geometric data

Definition at line 381 of file coverage_env_utils.py.

get_voronoi_features()

torch.Tensor get_voronoi_features ( CoverageSystem env )

static

Get voronoi features.

Parameters

env	coverage environment

Returns

torch voronoi features

Definition at line 290 of file coverage_env_utils.py.

get_weights()

torch.Tensor get_weights ( CoverageSystem env, Parameters params )

static

Get edge weights for the communication graph.

Parameters

env	coverage environment
params	parameters

Returns

torch edge weights

Definition at line 325 of file coverage_env_utils.py.

resize_maps()

torch.Tensor resize_maps ( torch.Tensor maps, int resized_map_size )

static

Resize maps to a given size Uses bilinear interpolation from torchvision.transforms.functional.resize Options antialias=True.

Parameters

maps	input maps
resized_map_size	size of the resized maps

Returns

torch resized maps

Definition at line 217 of file coverage_env_utils.py.

robot_positions_to_edge_weights()

torch.Tensor robot_positions_to_edge_weights ( PointVector robot_positions, int world_map_size, float comm_range )

static

Convert robot positions to edge weights.

Parameters

robot_positions	robot positions
world_map_size	size of the world map
comm_range	communication range

Returns

torch edge weights

Definition at line 353 of file coverage_env_utils.py.

to_tensor()

torch.Tensor to_tensor ( object data )

static

Converts various types of data to torch.Tensor.

   Can accept the following types:

- numpy.ndarray
- PointVector
- DblVectorVector
- DblVector

Parameters

data	input data

Returns

torch converted data

Exceptions

ValueError

if data type is not supported

Definition at line 70 of file coverage_env_utils.py.