Merge branch 'main' into apoddubny/ci-updates

CONTRIBUTORS.md

@@ -49,6 +49,7 @@ Guidelines for modifications:
 * Johnson Sun
 * Kaixi Bao
 * Kourosh Darvish
+* Lionel Gulich
 * Lorenz Wellhausen
 * Masoud Moghani
 * Michael Gussert

docs/source/how-to/save_camera_output.rst

@@ -89,7 +89,7 @@ To run the accompanying script, execute the following command:
 .. code-block:: bash
 
    # Usage with saving and drawing
-   ./isaaclab.sh -p source/standalone/tutorials/04_sensors/run_usd_camera.py --save --draw
+   ./isaaclab.sh -p source/standalone/tutorials/04_sensors/run_usd_camera.py --save --draw --enable_cameras
 
    # Usage with saving only in headless mode
    ./isaaclab.sh -p source/standalone/tutorials/04_sensors/run_usd_camera.py --save --headless --enable_cameras

docs/source/overview/teleop_imitation.rst

@@ -60,7 +60,7 @@ format.
       # install python module (for robomimic)
       ./isaaclab.sh -i robomimic
       # split data
-      ./isaaclab.sh -p source/standalone//workflows/robomimic/tools/split_train_val.py logs/robomimic/Isaac-Lift-Cube-Franka-IK-Rel-v0/hdf_dataset.hdf5 --ratio 0.2
+      ./isaaclab.sh -p source/standalone/workflows/robomimic/tools/split_train_val.py logs/robomimic/Isaac-Lift-Cube-Franka-IK-Rel-v0/hdf_dataset.hdf5 --ratio 0.2
 
 3. Train a BC agent for ``Isaac-Lift-Cube-Franka-IK-Rel-v0`` with
    `Robomimic <https://robomimic.github.io/>`__:

docs/source/tutorials/04_sensors/add_sensors_on_robot.rst

@@ -174,7 +174,7 @@ Now that we have gone through the code, let's run the script and see the result:
 
 .. code-block:: bash
 
-   ./isaaclab.sh -p source/standalone/tutorials/04_sensors/add_sensors_on_robot.py --num_envs 2
+   ./isaaclab.sh -p source/standalone/tutorials/04_sensors/add_sensors_on_robot.py --num_envs 2 --enable_cameras
 
 
 This command should open a stage with a ground plane, lights, and two quadrupedal robots.

pyproject.toml

@@ -46,6 +46,7 @@ known_third_party = [
     "omni.kit.*",
     "warp",
     "carb",
+    "Semantics",
 ]
 # Imports from this repository
 known_first_party = "omni.isaac.lab"

source/extensions/omni.isaac.lab/config/extension.toml

@@ -1,7 +1,7 @@
 [package]
 
 # Note: Semantic Versioning is used: https://semver.org/
-version = "0.24.13"
+version = "0.24.19"
 
 # Description
 title = "Isaac Lab framework for Robot Learning"

source/extensions/omni.isaac.lab/docs/CHANGELOG.rst

@@ -1,24 +1,68 @@
 Changelog
 ---------
 
-0.22.15 (2024-09-20)
+0.24.19 (2024-10-05)
 ~~~~~~~~~~~~~~~~~~~~
 
 Added
 ^^^^^
 
-* Added :meth:`grab_images` to be able to use images for an observation term in manager based environments
+* Added new functionalities to the FrameTransformer to make it more general. It is now possible to track:
+
+  * Target frames that aren't children of the source frame prim_path
+  * Target frames that are based upon the source frame prim_path
+
+
+0.24.18 (2024-10-04)
+~~~~~~~~~~~~~~~~~~~~
+
+Fixed
+^^^^^
+
+* Fixes parsing and application of ``size`` parameter for :class:`~omni.isaac.lab.sim.spawn.GroundPlaneCfg` to correctly
+  scale the grid-based ground plane.
+
+
+0.24.17 (2024-10-04)
+~~~~~~~~~~~~~~~~~~~~
+
+Fixed
+^^^^^
+
+* Fixed the deprecation notice for using ``pxr.Semantics``. The corresponding modules use ``Semantics`` module
+  directly.
+
+
+0.24.16 (2024-10-03)
+~~~~~~~~~~~~~~~~~~~~
+
+Changed
+^^^^^^^
+
+* Renamed the observation function :meth:`grab_images` to :meth:`image` to follow convention of noun-based naming.
+* Renamed the function :meth:`convert_perspective_depth_to_orthogonal_depth` to a shorter name
+  :meth:`omni.isaac.lab.utils.math.orthogonalize_perspective_depth`.
+
+
+0.24.15 (2024-09-20)
+~~~~~~~~~~~~~~~~~~~~
+
+Added
+^^^^^
+
+* Added :meth:`grab_images` to be able to use images for an observation term in manager-based environments.
+
 
 0.24.14 (2024-09-20)
 ~~~~~~~~~~~~~~~~~~~~
 
 Added
 ^^^^^
 
-* Added :meth:`convert_perspective_depth_to_orthogonal_depth`. :meth:`unproject_depth` assumes
-  that the input depth image is orthogonal. The new :meth:`convert_perspective_depth_to_orthogonal_depth`
-  can be used to convert a perspective depth image into an orthogonal depth image, so that the point cloud
-  can be unprojected correctly with :meth:`unproject_depth`.
+* Added the method :meth:`convert_perspective_depth_to_orthogonal_depth` to convert perspective depth
+  images to orthogonal depth images. This is useful for the :meth:`~omni.isaac.lab.utils.math.unproject_depth`,
+  since it expects orthogonal depth images as inputs.
+
 
 0.24.13 (2024-09-08)
 ~~~~~~~~~~~~~~~~~~~~

source/extensions/omni.isaac.lab/omni/isaac/lab/envs/direct_marl_env.py

@@ -81,7 +81,7 @@ def __init__(self, cfg: DirectMARLEnvCfg, render_mode: str | None = None, **kwar
 
         # set the seed for the environment
         if self.cfg.seed is not None:
-            self.seed(self.cfg.seed)
+            self.cfg.seed = self.seed(self.cfg.seed)
         else:
             carb.log_warn("Seed not set for the environment. The environment creation may not be deterministic.")
 

source/extensions/omni.isaac.lab/omni/isaac/lab/envs/direct_rl_env.py

@@ -86,7 +86,7 @@ def __init__(self, cfg: DirectRLEnvCfg, render_mode: str | None = None, **kwargs
 
         # set the seed for the environment
         if self.cfg.seed is not None:
-            self.seed(self.cfg.seed)
+            self.cfg.seed = self.seed(self.cfg.seed)
         else:
             carb.log_warn("Seed not set for the environment. The environment creation may not be deterministic.")
 

source/extensions/omni.isaac.lab/omni/isaac/lab/envs/manager_based_env.py

@@ -76,7 +76,7 @@ def __init__(self, cfg: ManagerBasedEnvCfg):
 
         # set the seed for the environment
         if self.cfg.seed is not None:
-            self.seed(self.cfg.seed)
+            self.cfg.seed = self.seed(self.cfg.seed)
         else:
             carb.log_warn("Seed not set for the environment. The environment creation may not be deterministic.")
 

source/extensions/omni.isaac.lab/omni/isaac/lab/envs/mdp/observations.py

@@ -182,38 +182,52 @@ def body_incoming_wrench(env: ManagerBasedEnv, asset_cfg: SceneEntityCfg) -> tor
     return link_incoming_forces.view(env.num_envs, -1)
 
 
-def grab_images(
+def image(
     env: ManagerBasedEnv,
     sensor_cfg: SceneEntityCfg = SceneEntityCfg("tiled_camera"),
     data_type: str = "rgb",
     convert_perspective_to_orthogonal: bool = False,
     normalize: bool = True,
 ) -> torch.Tensor:
-    """Grab all of the latest images of a specific datatype produced by a specific camera.
+    """Images of a specific datatype from the camera sensor.
+
+    If the flag :attr:`normalize` is True, post-processing of the images are performed based on their
+    data-types:
+
+    - "rgb": Scales the image to (0, 1) and subtracts with the mean of the current image batch.
+    - "depth" or "distance_to_camera" or "distance_to_plane": Replaces infinity values with zero.
 
     Args:
         env: The environment the cameras are placed within.
         sensor_cfg: The desired sensor to read from. Defaults to SceneEntityCfg("tiled_camera").
         data_type: The data type to pull from the desired camera. Defaults to "rgb".
-        convert_perspective_to_orthogonal: Whether to convert perspective
-            depth images to orthogonal depth images. Defaults to False.
-        normalize: Set to True to normalize images. Defaults to True.
+        convert_perspective_to_orthogonal: Whether to orthogonalize perspective depth images.
+            This is used only when the data type is "distance_to_camera". Defaults to False.
+        normalize: Whether to normalize the images. This depends on the selected data type.
+            Defaults to True.
 
     Returns:
-        The images produced at the last timestep
+        The images produced at the last time-step
     """
+    # extract the used quantities (to enable type-hinting)
     sensor: TiledCamera | Camera | RayCasterCamera = env.scene.sensors[sensor_cfg.name]
+
+    # obtain the input image
     images = sensor.data.output[data_type]
+
+    # depth image conversion
     if (data_type == "distance_to_camera") and convert_perspective_to_orthogonal:
-        images = math_utils.convert_perspective_depth_to_orthogonal_depth(images, sensor.data.intrinsic_matrices)
+        images = math_utils.orthogonalize_perspective_depth(images, sensor.data.intrinsic_matrices)
 
+    # rgb/depth image normalization
     if normalize:
         if data_type == "rgb":
-            images = images / 255
+            images = images.float() / 255.0
             mean_tensor = torch.mean(images, dim=(1, 2), keepdim=True)
             images -= mean_tensor
         elif "distance_to" in data_type or "depth" in data_type:
             images[images == float("inf")] = 0
+
     return images.clone()