Merge branch 'isaac-sim:main' into main

docs/source/api/lab/omni.isaac.lab.app.rst

@@ -28,6 +28,12 @@ The following details the behavior of the class based on the environment variabl
   * ``LIVESTREAM=2`` enables streaming  via the `WebRTC Livestream`_ extension. This allows users to
     connect in a browser using the WebRTC protocol.
 
+  .. note::
+
+    Each Isaac Sim instance can only connect to one streaming client.
+    Connecting to an Isaac Sim instance that is currently serving a streaming client
+    results in an error for the second user.
+
 * **Enable cameras**: If the environment variable ``ENABLE_CAMERAS`` is set to 1, then the
   cameras are enabled. This is useful for running the simulator without a GUI but still rendering the
   viewport and camera images.

docs/source/features/actuators.rst

@@ -47,7 +47,7 @@ Actuator groups
 ---------------
 
 The actuator models by themselves are computational blocks that take as inputs the desired joint commands
-and output the the joint commands to apply into the simulator. They do not contain any knowledge about the
+and output the joint commands to apply into the simulator. They do not contain any knowledge about the
 joints they are acting on themselves. These are handled by the :class:`omni.isaac.lab.assets.Articulation`
 class, which wraps around the physics engine's articulation class.
 
@@ -67,4 +67,4 @@ The following figure shows the actuator groups for a legged mobile manipulator:
 .. seealso::
 
     We provide implementations for various explicit actuator models. These are detailed in
-    `omni.isaac.lab.actuators <../api/lab.actuators.html>`_ sub-package.
+    `omni.isaac.lab.actuators <../api/lab/omni.isaac.lab.actuators.html>`_ sub-package.

docs/source/features/environments.rst

@@ -146,6 +146,10 @@ Environments based on legged locomotion tasks.
     +------------------------------+----------------------------------------------+------------------------------------------------------------------------------+
     | |velocity-rough-h1|          | |velocity-rough-h1-link|                     | Track a velocity command on rough terrain with the Unitree H1 robot          |
     +------------------------------+----------------------------------------------+------------------------------------------------------------------------------+
+    | |velocity-flat-g1|           | |velocity-flat-g1-link|                      | Track a velocity command on flat terrain with the Unitree G1 robot           |
+    +------------------------------+----------------------------------------------+------------------------------------------------------------------------------+
+    | |velocity-rough-g1|          | |velocity-rough-g1-link|                     | Track a velocity command on rough terrain with the Unitree G1 robot          |
+    +------------------------------+----------------------------------------------+------------------------------------------------------------------------------+
 
 .. |velocity-flat-anymal-b-link| replace:: `Isaac-Velocity-Flat-Anymal-B-v0 <https://github.com/isaac-sim/IsaacLab/blob/main/source/extensions/omni.isaac.lab_tasks/omni/isaac/lab_tasks/manager_based/locomotion/velocity/config/anymal_b/flat_env_cfg.py>`__
 .. |velocity-rough-anymal-b-link| replace:: `Isaac-Velocity-Rough-Anymal-B-v0 <https://github.com/isaac-sim/IsaacLab/blob/main/source/extensions/omni.isaac.lab_tasks/omni/isaac/lab_tasks/manager_based/locomotion/velocity/config/anymal_b/rough_env_cfg.py>`__
@@ -173,6 +177,9 @@ Environments based on legged locomotion tasks.
 .. |velocity-flat-h1-link| replace:: `Isaac-Velocity-Flat-H1-v0 <https://github.com/isaac-sim/IsaacLab/blob/main/source/extensions/omni.isaac.lab_tasks/omni/isaac/lab_tasks/manager_based/locomotion/velocity/config/h1/flat_env_cfg.py>`__
 .. |velocity-rough-h1-link| replace:: `Isaac-Velocity-Rough-H1-v0 <https://github.com/isaac-sim/IsaacLab/blob/main/source/extensions/omni.isaac.lab_tasks/omni/isaac/lab_tasks/manager_based/locomotion/velocity/config/h1/rough_env_cfg.py>`__
 
+.. |velocity-flat-g1-link| replace:: `Isaac-Velocity-Flat-G1-v0 <https://github.com/isaac-sim/IsaacLab/blob/main/source/extensions/omni.isaac.lab_tasks/omni/isaac/lab_tasks/manager_based/locomotion/velocity/config/g1/flat_env_cfg.py>`__
+.. |velocity-rough-g1-link| replace:: `Isaac-Velocity-Rough-G1-v0 <https://github.com/isaac-sim/IsaacLab/blob/main/source/extensions/omni.isaac.lab_tasks/omni/isaac/lab_tasks/manager_based/locomotion/velocity/config/g1/rough_env_cfg.py>`__
+
 
 .. |velocity-flat-anymal-b| image:: ../_static/tasks/locomotion/anymal_b_flat.jpg
 .. |velocity-rough-anymal-b| image:: ../_static/tasks/locomotion/anymal_b_rough.jpg
@@ -189,6 +196,8 @@ Environments based on legged locomotion tasks.
 .. |velocity-flat-spot| image:: ../_static/tasks/locomotion/spot_flat.jpg
 .. |velocity-flat-h1| image:: ../_static/tasks/locomotion/h1_flat.jpg
 .. |velocity-rough-h1| image:: ../_static/tasks/locomotion/h1_rough.jpg
+.. |velocity-flat-g1| image:: ../_static/tasks/locomotion/g1_flat.jpg
+.. |velocity-rough-g1| image:: ../_static/tasks/locomotion/g1_rough.jpg
 
 Navigation
 ----------

docs/source/features/tiled_rendering.rst

@@ -11,6 +11,8 @@ Tiled Rendering
 
     This feature is only available from Isaac Sim version 4.0.0.
 
+    Tiled rendering requires heavy memory resources. We recommend running at most 256 cameras in the scene.
+
 Tiled rendering APIs provide a vectorized interface for collecting data from camera sensors.
 This is useful for reinforcement learning environments requiring vision in the loop.
 Tiled rendering works by concatenating camera outputs from multiple cameras and rendering

docs/source/setup/faq.rst

@@ -80,8 +80,8 @@ to Isaac Lab, please reach out to us.
 .. _PhysX: https://developer.nvidia.com/physx-sdk
 .. _Isaac Sim: https://developer.nvidia.com/isaac-sim
 .. _Isaac Gym: https://developer.nvidia.com/isaac-gym
-.. _IsaacGymEnvs: https://github.com/NVIDIA-Omniverse/IsaacGymEnvs
-.. _OmniIsaacGymEnvs: https://github.com/NVIDIA-Omniverse/OmniIsaacGymEnvs
+.. _IsaacGymEnvs: https://github.com/isaac-sim/IsaacGymEnvs
+.. _OmniIsaacGymEnvs: https://github.com/isaac-sim/OmniIsaacGymEnvs
 .. _Orbit: https://isaac-orbit.github.io/orbit
 .. _Isaac Automator: https://github.com/isaac-sim/IsaacAutomator
 .. _migration guides: ../migration/index.html

docs/source/setup/installation/cloud_installation.rst

@@ -10,6 +10,8 @@ The result is a fully configured remote desktop cloud workstation, which can be
 Installing Isaac Automator
 --------------------------
 
+For the most update-to-date and complete installation instructions, please refer to `Isaac Automator <https://github.com/isaac-sim/IsaacAutomator?tab=readme-ov-file#installation>`__.
+
 To use Isaac Automator, first clone the repo:
 
 .. code-block:: bash
@@ -49,9 +51,31 @@ Running Isaac Automator
 
 To run Isaac Automator, first build the Isaac Automator container:
 
-.. code-block:: bash
+.. tabs::
+
+  .. tab:: Linux
+      .. code-block:: bash
+
+         ./build
+
+  .. tab:: Windows
+      .. code-block:: bash
+
+         docker build --platform linux/x86_64 -t isa .
+
+Next, enter the automator container:
+
+.. tabs::
+
+  .. tab:: Linux
+      .. code-block:: bash
+
+          ./run
+
+  .. tab:: Windows
+      .. code-block:: bash
 
-   ./build
+          docker run --platform linux/x86_64 -it --rm -v .:/app isa bash
 
 Next, run the deployed script for your preferred cloud:
 

docs/source/setup/sample.rst

@@ -215,7 +215,7 @@ from the environments into the respective libraries function argument and return
       # run script for training
       ./isaaclab.sh -p source/standalone/workflows/rsl_rl/train.py --task Isaac-Reach-Franka-v0 --headless
       # run script for playing with 32 environments
-      ./isaaclab.sh -p source/standalone/workflows/rsl_rl/play.py --task Isaac-Reach-Franka-v0 --num_envs 32 --checkpoint /PATH/TO/model.pth
+      ./isaaclab.sh -p source/standalone/workflows/rsl_rl/play.py --task Isaac-Reach-Franka-v0 --num_envs 32 --load_run run_folder_name --checkpoint model.pt
 
 All the scripts above log the training progress to `Tensorboard`_ in the ``logs`` directory in the root of
 the repository. The logs directory follows the pattern ``logs/<library>/<task>/<date-time>``, where ``<library>``

source/extensions/omni.isaac.lab/omni/isaac/lab/assets/articulation/articulation.py

@@ -345,7 +345,7 @@ def write_joint_state_to_sim(
             physx_env_ids = self._ALL_INDICES
         if joint_ids is None:
             joint_ids = slice(None)
-        elif env_ids != slice(None):
+        if env_ids != slice(None) and joint_ids != slice(None):
             env_ids = env_ids[:, None]
         # set into internal buffers
         self._data.joint_pos[env_ids, joint_ids] = position
@@ -377,7 +377,7 @@ def write_joint_stiffness_to_sim(
             physx_env_ids = self._ALL_INDICES
         if joint_ids is None:
             joint_ids = slice(None)
-        elif env_ids != slice(None):
+        if env_ids != slice(None) and joint_ids != slice(None):
             env_ids = env_ids[:, None]
         # set into internal buffers
         self._data.joint_stiffness[env_ids, joint_ids] = stiffness
@@ -407,7 +407,7 @@ def write_joint_damping_to_sim(
             physx_env_ids = self._ALL_INDICES
         if joint_ids is None:
             joint_ids = slice(None)
-        elif env_ids != slice(None):
+        if env_ids != slice(None) and joint_ids != slice(None):
             env_ids = env_ids[:, None]
         # set into internal buffers
         self._data.joint_damping[env_ids, joint_ids] = damping
@@ -435,7 +435,7 @@ def write_joint_effort_limit_to_sim(
             physx_env_ids = self._ALL_INDICES
         if joint_ids is None:
             joint_ids = slice(None)
-        elif env_ids != slice(None):
+        if env_ids != slice(None) and joint_ids != slice(None):
             env_ids = env_ids[:, None]
         # move tensor to cpu if needed
         if isinstance(limits, torch.Tensor):
@@ -466,7 +466,7 @@ def write_joint_armature_to_sim(
             physx_env_ids = self._ALL_INDICES
         if joint_ids is None:
             joint_ids = slice(None)
-        elif env_ids != slice(None):
+        if env_ids != slice(None) and joint_ids != slice(None):
             env_ids = env_ids[:, None]
         # set into internal buffers
         self._data.joint_armature[env_ids, joint_ids] = armature
@@ -493,7 +493,7 @@ def write_joint_friction_to_sim(
             physx_env_ids = self._ALL_INDICES
         if joint_ids is None:
             joint_ids = slice(None)
-        elif env_ids != slice(None):
+        if env_ids != slice(None) and joint_ids != slice(None):
             env_ids = env_ids[:, None]
         # set into internal buffers
         self._data.joint_friction[env_ids, joint_ids] = joint_friction
@@ -521,7 +521,7 @@ def write_joint_limits_to_sim(
             physx_env_ids = self._ALL_INDICES
         if joint_ids is None:
             joint_ids = slice(None)
-        elif env_ids != slice(None):
+        if env_ids != slice(None) and joint_ids != slice(None):
             env_ids = env_ids[:, None]
         # set into internal buffers
         self._data.joint_limits[env_ids, joint_ids] = limits
@@ -551,7 +551,7 @@ def set_joint_position_target(
             env_ids = slice(None)
         if joint_ids is None:
             joint_ids = slice(None)
-        elif env_ids != slice(None):
+        if env_ids != slice(None) and joint_ids != slice(None):
             env_ids = env_ids[:, None]
         # set targets
         self._data.joint_pos_target[env_ids, joint_ids] = target
@@ -575,7 +575,7 @@ def set_joint_velocity_target(
             env_ids = slice(None)
         if joint_ids is None:
             joint_ids = slice(None)
-        elif env_ids != slice(None):
+        if env_ids != slice(None) and joint_ids != slice(None):
             env_ids = env_ids[:, None]
         # set targets
         self._data.joint_vel_target[env_ids, joint_ids] = target
@@ -599,7 +599,7 @@ def set_joint_effort_target(
             env_ids = slice(None)
         if joint_ids is None:
             joint_ids = slice(None)
-        elif env_ids != slice(None):
+        if env_ids != slice(None) and joint_ids != slice(None):
             env_ids = env_ids[:, None]
         # set targets
         self._data.joint_effort_target[env_ids, joint_ids] = target
@@ -626,7 +626,7 @@ def set_fixed_tendon_stiffness(
             env_ids = slice(None)
         if fixed_tendon_ids is None:
             fixed_tendon_ids = slice(None)
-        elif env_ids != slice(None):
+        if env_ids != slice(None) and fixed_tendon_ids != slice(None):
             env_ids = env_ids[:, None]
         # set stiffness
         self._data.fixed_tendon_stiffness[env_ids, fixed_tendon_ids] = stiffness
@@ -653,7 +653,7 @@ def set_fixed_tendon_damping(
             env_ids = slice(None)
         if fixed_tendon_ids is None:
             fixed_tendon_ids = slice(None)
-        elif env_ids != slice(None):
+        if env_ids != slice(None) and fixed_tendon_ids != slice(None):
             env_ids = env_ids[:, None]
         # set damping
         self._data.fixed_tendon_damping[env_ids, fixed_tendon_ids] = damping
@@ -680,7 +680,7 @@ def set_fixed_tendon_limit_stiffness(
             env_ids = slice(None)
         if fixed_tendon_ids is None:
             fixed_tendon_ids = slice(None)
-        elif env_ids != slice(None):
+        if env_ids != slice(None) and fixed_tendon_ids != slice(None):
             env_ids = env_ids[:, None]
         # set limit_stiffness
         self._data.fixed_tendon_limit_stiffness[env_ids, fixed_tendon_ids] = limit_stiffness
@@ -707,7 +707,7 @@ def set_fixed_tendon_limit(
             env_ids = slice(None)
         if fixed_tendon_ids is None:
             fixed_tendon_ids = slice(None)
-        elif env_ids != slice(None):
+        if env_ids != slice(None) and fixed_tendon_ids != slice(None):
             env_ids = env_ids[:, None]
         # set limit
         self._data.fixed_tendon_limit[env_ids, fixed_tendon_ids] = limit
@@ -734,7 +734,7 @@ def set_fixed_tendon_rest_length(
             env_ids = slice(None)
         if fixed_tendon_ids is None:
             fixed_tendon_ids = slice(None)
-        elif env_ids != slice(None):
+        if env_ids != slice(None) and fixed_tendon_ids != slice(None):
             env_ids = env_ids[:, None]
         # set rest_length
         self._data.fixed_tendon_rest_length[env_ids, fixed_tendon_ids] = rest_length
@@ -761,7 +761,7 @@ def set_fixed_tendon_offset(
             env_ids = slice(None)
         if fixed_tendon_ids is None:
             fixed_tendon_ids = slice(None)
-        elif env_ids != slice(None):
+        if env_ids != slice(None) and fixed_tendon_ids != slice(None):
             env_ids = env_ids[:, None]
         # set offset
         self._data.fixed_tendon_offset[env_ids, fixed_tendon_ids] = offset