using replica dataset in habitat with ros

[mmahdavian]

Hi

I've tried your ros codes with habitat and it's great.thank you for them. I am trying to import replica dataset into habitat and then use your ros nodes to get image data and input cmd_vel.I do you know how can I change the environment in your codes? Right now it only shows skokloster-castle.navmesh environment and I can't change it. I tried to change "habitat/config/default.py" file to show van-gogh-room as an example, but it doesn't work. I also tried van-gogh-room.navmesh and it didn't work either. Do you know how can I change env to van-gogh-room or replica?

Thank You

DATASET:
  CONTENT_SCENES: ['*']
  DATA_PATH: data/datasets/pointnav/habitat-test-scenes/v1/{split}/{split}.json.gz
  NUM_EPISODE_SAMPLE: -1
  SCENES_DIR: /home/mohammad/Mohammad_ws/habitat/habitat-api/data/scene_datasets/
  SPLIT: train
  TYPE: PointNav-v1
ENVIRONMENT:
  MAX_EPISODE_SECONDS: 10000000
  MAX_EPISODE_STEPS: 500
SEED: 100
SIMULATOR:
  ACTION_SPACE_CONFIG: v0
  AGENTS: ['AGENT_0']
  AGENT_0:
    ANGULAR_ACCELERATION: 12.56
    ANGULAR_FRICTION: 1.0
    COEFFICIENT_OF_RESTITUTION: 0.0
    HEIGHT: 1.5
    IS_SET_START_STATE: False
    LINEAR_ACCELERATION: 20.0
    LINEAR_FRICTION: 0.5
    MASS: 32.0
    RADIUS: 0.1
    SENSORS: ['RGB_SENSOR']
    START_POSITION: [0, 0, 0]
    START_ROTATION: [0, 0, 0, 1]
  BC_SENSOR:
    HEIGHT: 480
    HFOV: 90
    POSITION: [0, 1.25, 0]
    TYPE: HabitatSimBCSensor
    WIDTH: 640
  DEFAULT_AGENT_ID: 0
  DEPTH_SENSOR:
    HEIGHT: 256
    HFOV: 90
    MAX_DEPTH: 10
    MIN_DEPTH: 0
    NORMALIZE_DEPTH: True
    POSITION: [0, 1.25, 0]
    TYPE: HabitatSimDepthSensor
    WIDTH: 256
  FORWARD_STEP_SIZE: 0.25
  HABITAT_SIM_V0:
    GPU_DEVICE_ID: 0
  RGB_SENSOR:
    HEIGHT: 256
    HFOV: 90
    POSITION: [0, 1.25, 0]
    TYPE: HabitatSimRGBSensor
    WIDTH: 256
  SCENE: data/scene_datasets/habitat-test-scenes/van-gogh-room.glb
  SEED: 100
  SEMANTIC_SENSOR:
    HEIGHT: 480
    HFOV: 90
    POSITION: [0, 1.25, 0]
    TYPE: HabitatSimSemanticSensor
    WIDTH: 640
  TILT_ANGLE: 15
  TURN_ANGLE: 10
  TYPE: Sim-v0
TASK:
  COLLISIONS:
    TYPE: Collisions
  GOAL_SENSOR_UUID: pointgoal
  HEADING_SENSOR:
    TYPE: HeadingSensor
  MEASUREMENTS: ['SPL']
  POINTGOAL_SENSOR:
    GOAL_FORMAT: POLAR
    TYPE: PointGoalSensor
  PROXIMITY_SENSOR:
    MAX_DETECTION_RADIUS: 2.0
    TYPE: ProximitySensor
  SENSORS: ['POINTGOAL_SENSOR']
  SPL:
    SUCCESS_DISTANCE: 0.2
    TYPE: SPL
  STATIC_POINTGOAL_SENSOR:
    GOAL_FORMAT: CARTESIAN
    TYPE: StaticPointGoalSensor
  SUCCESS_DISTANCE: 0.2
  TOP_DOWN_MAP:
    DRAW_BORDER: True
    DRAW_SHORTEST_PATH: True
    DRAW_SOURCE_AND_TARGET: True
    FOG_OF_WAR:
      DRAW: True
      FOV: 90
      VISIBILITY_DIST: 5.0
    MAP_PADDING: 3
    MAP_RESOLUTION: 1250
    MAX_EPISODE_STEPS: 1000
    NUM_TOPDOWN_MAP_SAMPLE_POINTS: 20000
    TYPE: TopDownMap
  TYPE: Nav-v0
2020-11-26 15:58:30,207 initializing sim Sim-v0
Renderer: GeForce RTX 2080 Ti/PCIe/SSE2 by NVIDIA Corporation
OpenGL version: 4.6.0 NVIDIA 440.33.01
Using optional features:
    GL_ARB_ES2_compatibility
    GL_ARB_direct_state_access
    GL_ARB_get_texture_sub_image
    GL_ARB_invalidate_subdata
    GL_ARB_multi_bind
    GL_ARB_robustness
    GL_ARB_separate_shader_objects
    GL_ARB_texture_filter_anisotropic
    GL_ARB_texture_storage
    GL_ARB_texture_storage_multisample
    GL_ARB_vertex_array_object
    GL_KHR_debug
Using driver workarounds:
    no-layout-qualifiers-on-old-glsl
    nv-zero-context-profile-mask
    nv-implementation-color-read-format-dsa-broken
    nv-cubemap-inconsistent-compressed-image-size
    nv-cubemap-broken-full-compressed-image-query
    nv-compressed-block-size-in-bits
I1126 15:58:30.934998 18023 simulator.py:80] Loaded navmesh /home/mohammad/Mohammad_ws/habitat/habitat-api/data/scene_datasets/habitat-test-scenes/skokloster-castle.navmesh
2020-11-26 15:58:30,935 initializing task Nav-v0