Skip to content

K
KincoActuatorIsaacLab
Commit 06715c2c authored by David Hoeller's avatar David Hoeller
Browse files
Options

Restructures the documentation (#126) 

# Description

- Restructures the documentation
- Adds tabs for commands on Windows
- Updates PhysX links with correct versions

## Type of change

- New feature (non-breaking change which adds functionality)

## Checklist

- [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with
`./isaaclab.sh --format`
- [ ] I have made corresponding changes to the documentation
- [x] My changes generate no new warnings
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have updated the changelog and the corresponding version in the
extension's `config/extension.toml` file
- [x] I have added my name to the `CONTRIBUTORS.md` or my name already
exists there
parent 4f8b2b57
Hide whitespace changes
Inline Side-by-side
Showing with 979 additions and 500 deletions
docs/index.rst
View file @ 06715c2c
......@@ -10,14 +10,6 @@ in robotics research (such as reinforcement learning, learning from demonstratio
`NVIDIA Isaac Sim`_ to leverage the latest simulation capabilities for photo-realistic scenes, and fast
and efficient simulation.
Isaac Lab provides over 26 environments, and we are actively working on adding more environments to the list. Current environments include Classic tasks - Cartpole, Cartpole with camera, Humanoid and Ant, fixed-arm and dexterous manipulation tasks - UR10, Franka, Allegro, Shadow Hand, Legged locomotion tasks - Quadrupeds and Humanoids, Navigation tasks - Quadruped, and Quadcopter. It features over 16 robots:
- Classic - Cartpole, Humanoid, Ant
- Fixed-Arms and Hands - UR10, Franka, Allegro, Shadow Hand
- Quadrupeds – Anybotics Anymal-B, Anymal-C, Anymal-D, Unitree A1, Unitree Go1, Unitree Go2, Boston Dynamics Spot
- Humanoids - Unitree H1, Unitree G1
- Quadcopter - Crazyflie
The core objectives of the framework are:
- **Modularity**: Easily customize and add new environments, robots, and sensors.
......@@ -29,6 +21,19 @@ Key features available in Isaac Lab include fast and accurate physics simulation
tiled rendering APIs for vectorized rendering, domain randomization for improving robustness and adaptability,
and support for running in the cloud.
Additionally, Isaac Lab provides over 26 environments, and we are actively working on adding more environments
to the list. These include classic control tasks, fixed-arm and dexterous manipulation tasks, legged locomotion tasks,
and navigation tasks. A complete list is in available in the `environments <source/overview/environments>`_ section.
The framework also includes over 16 robots. If you are looking to add a new robot, please refer to the
:ref:`how-to` section. The current list of robots includes:
- **Classic** Cartpole, Humanoid, Ant
- **Fixed-Arm and Hands**: UR10, Franka, Allegro, Shadow Hand
- **Quadrupeds**: Anybotics Anymal-B, Anymal-C, Anymal-D, Unitree A1, Unitree Go1, Unitree Go2, Boston Dynamics Spot
- **Humanoids**: Unitree H1, Unitree G1
- **Quadcopter**: Crazyflie
For more information about the framework, please refer to the `paper <https://arxiv.org/abs/2301.04195>`_
:cite:`mittal2023orbit`. For clarifications on NVIDIA Isaac ecosystem, please check out the
:doc:`/source/setup/faq` section.
......@@ -78,11 +83,23 @@ Table of Contents
:titlesonly:
source/overview/developer-guide/index
source/overview/environment-workflows/index
source/overview/core-concepts/index
source/overview/environments
source/overview/reinforcement-learning/index
source/overview/teleop_imitation
source/overview/basic_agents
source/overview/sample_scripts
.. toctree::
:maxdepth: 2
:caption: Features
source/features/hydra
source/features/multi_gpu
source/features/tiled_rendering
source/features/reproducibility
.. source/features/motion_generators
.. toctree::
:maxdepth: 1
:caption: Resources
......@@ -101,18 +118,6 @@ Table of Contents
source/migration/migrating_from_omniisaacgymenvs
source/migration/migrating_from_orbit
.. toctree::
:maxdepth: 2
:caption: Features
source/features/hydra
source/features/multi_gpu
source/features/tiled_rendering
source/features/environments
source/features/actuators
source/features/reproducibility
.. source/features/motion_generators
.. toctree::
:maxdepth: 1
:caption: Source API
......@@ -123,6 +128,7 @@ Table of Contents
:maxdepth: 1
:caption: References
source/refs/additional_resources
source/refs/contributing
source/refs/troubleshooting
source/refs/issues
......@@ -136,7 +142,7 @@ Table of Contents
GitHub <https://github.com/isaac-sim/IsaacLab>
NVIDIA Isaac Sim <https://docs.omniverse.nvidia.com/isaacsim/latest/index.html>
NVIDIA PhysX <https://nvidia-omniverse.github.io/PhysX/physx/5.4.0/index.html>
NVIDIA PhysX <https://nvidia-omniverse.github.io/PhysX/physx/5.4.1/index.html>
Indices and tables
==================
......
docs/source/features/tiled_rendering.rst
View file @ 06715c2c
Tiled Rendering and Recording
=============================
Tiled-Camera Rendering
======================
.. currentmodule:: omni.isaac.lab
Tiled Rendering
---------------
.. note::
This feature is only available from Isaac Sim version 4.2.0 onwards.
Tiled rendering in combination with image processing networks require heavy memory resources, especially at larger resolutions. We recommend running at 512 cameras in the scene on RTX 4090 GPUs or similar.
Tiled rendering in combination with image processing networks require heavy memory resources, especially
at larger resolutions. We recommend running at 512 cameras in the scene on RTX 4090 GPUs or similar.
Tiled rendering APIs provide a vectorized interface for collecting data from camera sensors.
......@@ -61,7 +58,7 @@ environment. For example:
Annotators and Data Types
^^^^^^^^^^^^^^^^^^^^^^^^^
-------------------------
Both :class:`~sensors.TiledCamera` and :class:`~sensors.Camera` classes provide APIs for retrieving various types annotator data from replicator:
......@@ -77,7 +74,7 @@ Both :class:`~sensors.TiledCamera` and :class:`~sensors.Camera` classes provide
* ``"instance_id_segmentation_fast"``: The instance id segmentation data.
RGB and RGBA
""""""""""""
~~~~~~~~~~~~
``rgb`` data type returns a 3-channel RGB colored image of type ``torch.uint8``, with dimension (B, H, W, 3).
......@@ -86,7 +83,7 @@ RGB and RGBA
To convert the ``torch.uint8`` data to ``torch.float32``, divide the buffer by 255.0 to obtain a ``torch.float32`` buffer containing data from 0 to 1.
Depth and Distances
"""""""""""""""""""
~~~~~~~~~~~~~~~~~~~
``distance_to_camera`` returns a single-channel depth image with distance to the camera optical center. The dimension for this annotator is (B, H, W, 1) and has type ``torch.float32``.
......@@ -95,63 +92,40 @@ Depth and Distances
``depth`` is provided as an alias for ``distance_to_image_plane`` and will return the same data as the ``distance_to_image_plane`` annotator, with dimension (B, H, W, 1) and type ``torch.float32``.
Normals
"""""""
~~~~~~~
``normals`` returns an image containing the local surface normal vectors at each pixel. The buffer has dimension (B, H, W, 3), containing the (x, y, z) information for each vector, and has data type ``torch.float32``.
Motion Vectors
""""""""""""""
~~~~~~~~~~~~~~
``motion_vectors`` returns the per-pixel motion vectors in image space, with a 2D array of motion vectors representing the relative motion of a pixel in the camera’s viewport between frames. The buffer has dimension (B, H, W, 2), representing x - the motion distance in the horizontal axis (image width) with movement to the left of the image being positive and movement to the right being negative and y - motion distance in the vertical axis (image height) with movement towards the top of the image being positive and movement to the bottom being negative. The data type is ``torch.float32``.
Semantic Segmentation
"""""""""""""""""""""
~~~~~~~~~~~~~~~~~~~~~
``semantic_segmentation`` outputs semantic segmentation of each entity in the camera’s viewport that has semantic labels. In addition to the image buffer, an ``info`` dictionary can be retrieved with ``tiled_camera.data.info['semantic_segmentation']`` containing ID to labels information.
If ``colorize_semantic_segmentation=True`` in the camera config, a 4-channel RGBA image will be returned with dimension (B, H, W, 4) and type ``torch.uint8``. The info ``idToLabels`` dictionary will be the mapping from color to semantic labels.
- If ``colorize_semantic_segmentation=True`` in the camera config, a 4-channel RGBA image will be returned with dimension (B, H, W, 4) and type ``torch.uint8``. The info ``idToLabels`` dictionary will be the mapping from color to semantic labels.
If ``colorize_semantic_segmentation=False``, a buffer of dimension (B, H, W, 1) of type ``torch.int32`` will be returned, containing the semantic ID of each pixel. The info ``idToLabels`` dictionary will be the mapping from semantic ID to semantic labels.
- If ``colorize_semantic_segmentation=False``, a buffer of dimension (B, H, W, 1) of type ``torch.int32`` will be returned, containing the semantic ID of each pixel. The info ``idToLabels`` dictionary will be the mapping from semantic ID to semantic labels.
Instance ID Segmentation
""""""""""""""""""""""""
~~~~~~~~~~~~~~~~~~~~~~~~
``instance_id_segmentation_fast`` outputs instance ID segmentation of each entity in the camera’s viewport. The instance ID is unique for each prim in the scene with different paths. In addition to the image buffer, an ``info`` dictionary can be retrieved with ``tiled_camera.data.info['instance_id_segmentation_fast']`` containing ID to labels information.
The main difference between ``instance_id_segmentation_fast`` and ``instance_segmentation_fast`` are that instance segmentation annotator goes down the hierarchy to the lowest level prim which has semantic labels, where instance ID segmentation always goes down to the leaf prim.
If ``colorize_instance_id_segmentation=True`` in the camera config, a 4-channel RGBA image will be returned with dimension (B, H, W, 4) and type ``torch.uint8``. The info ``idToLabels`` dictionary will be the mapping from color to USD prim path of that entity.
- If ``colorize_instance_id_segmentation=True`` in the camera config, a 4-channel RGBA image will be returned with dimension (B, H, W, 4) and type ``torch.uint8``. The info ``idToLabels`` dictionary will be the mapping from color to USD prim path of that entity.
If ``colorize_instance_id_segmentation=False``, a buffer of dimension (B, H, W, 1) of type ``torch.int32`` will be returned, containing the instance ID of each pixel. The info ``idToLabels`` dictionary will be the mapping from instance ID to USD prim path of that entity.
- If ``colorize_instance_id_segmentation=False``, a buffer of dimension (B, H, W, 1) of type ``torch.int32`` will be returned, containing the instance ID of each pixel. The info ``idToLabels`` dictionary will be the mapping from instance ID to USD prim path of that entity.
Instance Segmentation
"""""""""""""""""""""
``instance_segmentation_fast`` outputs instance segmentation of each entity in the camera’s viewport. In addition to the image buffer, an ``info`` dictionary can be retrieved with ``tiled_camera.data.info['instance_segmentation_fast']`` containing ID to labels and ID to semantic information.
If ``colorize_instance_segmentation=True`` in the camera config, a 4-channel RGBA image will be returned with dimension (B, H, W, 4) and type ``torch.uint8``. The info ``idToLabels`` dictionary will be the mapping from color to USD prim path of that semantic entity. The info ``idToSemantics`` dictionary will be the mapping from color to semantic labels of that semantic entity.
If ``colorize_instance_segmentation=False``, a buffer of dimension (B, H, W, 1) of type ``torch.int32`` will be returned, containing the instance ID of each pixel. The info ``idToLabels`` dictionary will be the mapping from instance ID to USD prim path of that semantic entity. The info ``idToSemantics`` dictionary will be the mapping from instance ID to semantic labels of that semantic entity.
Recording during training
-------------------------
Isaac Lab supports recording video clips during training using the `gymnasium.wrappers.RecordVideo <https://gymnasium.farama.org/main/_modules/gymnasium/wrappers/record_video/>`_ class.
This feature can be enabled by installing ``ffmpeg`` and using the following command line arguments with the training script:
* ``--video`` - enables video recording during training
* ``--video_length`` - length of each recorded video (in steps)
* ``--video_interval`` - interval between each video recording (in steps)
Make sure to also add the ``--enable_cameras`` argument when running headless.
Note that enabling recording is equivalent to enabling rendering during training, which will slow down both startup and runtime performance.
Example usage:
.. code-block:: shell
python source/standalone/workflows/rl_games/train.py --task=Isaac-Cartpole-v0 --headless --video --video_length 100 --video_interval 500
- If ``colorize_instance_segmentation=True`` in the camera config, a 4-channel RGBA image will be returned with dimension (B, H, W, 4) and type ``torch.uint8``. The info ``idToLabels`` dictionary will be the mapping from color to USD prim path of that semantic entity. The info ``idToSemantics`` dictionary will be the mapping from color to semantic labels of that semantic entity.
Recorded videos will be saved in the same directory as the training checkpoints, under ``IsaacLab/logs/<rl_workflow>/<task>/<run>/videos/train``.
- If ``colorize_instance_segmentation=False``, a buffer of dimension (B, H, W, 1) of type ``torch.int32`` will be returned, containing the instance ID of each pixel. The info ``idToLabels`` dictionary will be the mapping from instance ID to USD prim path of that semantic entity. The info ``idToSemantics`` dictionary will be the mapping from instance ID to semantic labels of that semantic entity.
docs/source/how-to/index.rst
View file @ 06715c2c
.. _how-to:
How-to Guides
=============
......@@ -10,15 +12,82 @@ use Isaac Lab. If you are new to Isaac Lab, we recommend you start with the tuto
This section is a work in progress. If you have a question that is not answered here,
please open an issue on our `GitHub page <https://github.com/isaac-sim/IsaacLab>`_.
Importing a New Asset
---------------------
Importing an asset into Isaac Lab is a common task. It contains two steps: importing the asset into
a USD format and then setting up the configuration object for the asset. The following guide explains
how to import a new asset into Isaac Lab.
.. toctree::
:maxdepth: 1
import_new_asset
write_articulation_cfg
Creating a Fixed Asset
----------------------
Often you may want to create a fixed asset in your scene. For instance, making a floating base robot
a fixed base robot. This guide goes over the various considerations and steps to create a fixed asset.
.. toctree::
:maxdepth: 1
make_fixed_prim
Saving Camera Output
--------------------
This guide explains how to save the camera output in Isaac Lab.
.. toctree::
:maxdepth: 1
save_camera_output
Drawing Markers
---------------
This guide explains how to use the :class:`~omni.isaac.lab.markers.VisualizationMarkers` class to draw markers in
Isaac Lab.
.. toctree::
:maxdepth: 1
draw_markers
Interfacing with Environments
-----------------------------
These guides explain how to interface with reinforcement learning environments in Isaac Lab.
.. toctree::
:maxdepth: 1
wrap_rl_env
add_own_library
master_omniverse
Recording an Animation and Video
--------------------------------
This guide explains how to record an animation and video in Isaac Lab.
.. toctree::
:maxdepth: 1
record_animation
record_video
Mastering Omniverse
-------------------
Omniverse is a powerful platform that provides a wide range of features. This guide links to
additional resources that help you use Omniverse features in Isaac Lab.
.. toctree::
:maxdepth: 1
master_omniverse
docs/source/how-to/record_video.rst 0 → 100644
View file @ 06715c2c
Recording video clips during training
=====================================
Isaac Lab supports recording video clips during training using the
`gymnasium.wrappers.RecordVideo <https://gymnasium.farama.org/main/_modules/gymnasium/wrappers/record_video/>`_ class.
This feature can be enabled by installing ``ffmpeg`` and using the following command line arguments with the training
script:
* ``--video``: enables video recording during training
* ``--video_length``: length of each recorded video (in steps)
* ``--video_interval``: interval between each video recording (in steps)
Make sure to also add the ``--enable_cameras`` argument when running headless.
Note that enabling recording is equivalent to enabling rendering during training, which will slow down both startup and runtime performance.
Example usage:
.. code-block:: shell
python source/standalone/workflows/rl_games/train.py --task=Isaac-Cartpole-v0 --headless --video --video_length 100 --video_interval 500
The recorded videos will be saved in the same directory as the training checkpoints, under
``IsaacLab/logs/<rl_workflow>/<task>/<run>/videos/train``.
docs/source/how-to/write_articulation_cfg.rst
View file @ 06715c2c
......@@ -84,7 +84,7 @@ Actuators are a crucial component of an articulation. Through this configuration
to define the type of actuator model to use. We can use the internal actuator model provided by
the physics engine (i.e. the implicit actuator model), or use a custom actuator model which is
governed by a user-defined system of equations (i.e. the explicit actuator model).
For more details on actuators, see :ref:`feature-actuators`.
For more details on actuators, see :ref:`overview-actuators`.
The cartpole's articulation has two actuators, one corresponding to its each joint:
``cart_to_pole`` and ``slider_to_cart``. We use two different actuator models for these actuators as
......
docs/source/overview/environment-workflows/basic_environments.rst → docs/source/overview/basic_agents.rst
View file @ 06715c2c
Environment Workflows
=====================
Basic Agents
============
Workflows
---------
......@@ -11,10 +11,22 @@ configuration file that defines the scene, observations, rewards and action spac
The list of environments available registered with OpenAI Gym can be found by running:
.. code:: bash
.. tab-set::
:sync-group: os
./isaaclab.sh -p source/standalone/environments/list_envs.py
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
./isaaclab.sh -p source/standalone/environments/list_envs.py
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
isaaclab.bat -p source\standalone\environments\list_envs.py
Basic agents
~~~~~~~~~~~~
......@@ -24,15 +36,41 @@ useful to ensure that the environments are configured correctly.
- Zero-action agent on the Cart-pole example
.. code:: bash
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
./isaaclab.sh -p source/standalone/environments/zero_agent.py --task Isaac-Cartpole-v0 --num_envs 32
./isaaclab.sh -p source/standalone/environments/zero_agent.py --task Isaac-Cartpole-v0 --num_envs 32
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
isaaclab.bat -p source\standalone\environments\zero_agent.py --task Isaac-Cartpole-v0 --num_envs 32
- Random-action agent on the Cart-pole example:
.. code:: bash
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
./isaaclab.sh -p source/standalone/environments/random_agent.py --task Isaac-Cartpole-v0 --num_envs 32
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
./isaaclab.sh -p source/standalone/environments/random_agent.py --task Isaac-Cartpole-v0 --num_envs 32
isaaclab.bat -p source\standalone\environments\random_agent.py --task Isaac-Cartpole-v0 --num_envs 32
State machine
......@@ -43,6 +81,40 @@ help in understanding the environment and how to use the provided interfaces.
The state machines are written in `warp <https://github.com/NVIDIA/warp>`__ which
allows efficient execution for large number of environments using CUDA kernels.
.. code:: bash
- Picking up a cube and placing it at a desired pose with a robotic arm:
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
./isaaclab.sh -p source/standalone/environments/state_machine/lift_cube_sm.py --num_envs 32
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
isaaclab.bat -p source\standalone\environments\state_machine\lift_cube_sm.py --num_envs 32
- Picking up a deformable teddy bear and placing it at a desired pose with a robotic arm:
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
./isaaclab.sh -p source/standalone/environments/state_machine/lift_teddy_bear.py
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
./isaaclab.sh -p source/standalone/environments/state_machine/lift_cube_sm.py --num_envs 32
isaaclab.bat -p source\standalone\environments\state_machine\lift_teddy_bear.py
docs/source/features/actuators.rst → docs/source/overview/core-concepts/actuators.rst
View file @ 06715c2c
.. _feature-actuators:
.. _overview-actuators:
Actuators
......@@ -59,13 +59,13 @@ actuator model, such as a DC motor, would require configuring a different actuat
The following figure shows the actuator groups for a legged mobile manipulator:
.. image:: ../_static/actuator-group/actuator-light.svg
.. image:: ../../_static/actuator-group/actuator-light.svg
:class: only-light
:align: center
:alt: Actuator models for a legged mobile manipulator
:width: 80%
.. image:: ../_static/actuator-group/actuator-dark.svg
.. image:: ../../_static/actuator-group/actuator-dark.svg
:class: only-dark
:align: center
:width: 80%
......
docs/source/overview/core-concepts/index.rst 0 → 100644
View file @ 06715c2c
Core Concepts
=============
This section we introduce core concepts in Isaac Lab.
.. toctree::
:maxdepth: 1
task_workflows
actuators
docs/source/overview/developer-guide/repo_structure.rst
View file @ 06715c2c
......@@ -8,7 +8,10 @@ The ``Isaac Lab`` repository is structured as follows:
IsaacLab
├── .vscode
├── .flake8
├── CONTRIBUTING.md
├── CONTRIBUTORS.md
├── LICENSE
├── isaaclab.bat
├── isaaclab.sh
├── pyproject.toml
├── README.md
......
docs/source/overview/environment-workflows/index.rst deleted 100644 → 0
View file @ 4f8b2b57
Introduction to Environments
============================
This section introduces fundamental concepts of environments and agents in Isaac Lab.
Example scripts are available to show implementations of basic agents and state machines.
In addition, we introduce the different task workflows available in Isaac Lab for
implementing new environments.
.. toctree::
:maxdepth: 1
basic_environments
task_workflows
docs/source/features/environments.rst → docs/source/overview/environments.rst
View file @ 06715c2c
Environments
============
.. _environments:
Available Environments
======================
The following lists comprises of all the RL tasks implementations that are available in Isaac Lab.
While we try to keep this list up-to-date, you can always get the latest list of environments by
running the following command:
.. code-block:: bash
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
./isaaclab.sh -p source/standalone/environments/list_envs.py
./isaaclab.sh -p source/standalone/environments/list_envs.py
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
isaaclab.bat -p source\standalone\environments\list_envs.py
We are actively working on adding more environments to the list. If you have any environments that
you would like to add to Isaac Lab, please feel free to open a pull request!
......@@ -27,14 +42,19 @@ Classic environments that are based on IsaacGymEnvs implementation of MuJoCo-sty
| World | Environment ID | Description |
+==================+=============================+=========================================================================+
| |humanoid| | |humanoid-link| | Move towards a direction with the MuJoCo humanoid robot |
| | | |
| | |humanoid-direct-link| | |
+------------------+-----------------------------+-------------------------------------------------------------------------+
| |ant| | |ant-link| | Move towards a direction with the MuJoCo ant robot |
| | | |
| | |ant-direct-link| | |
+------------------+-----------------------------+-------------------------------------------------------------------------+
| |cartpole| | |cartpole-link| | Move the cart to keep the pole upwards in the classic cartpole control |
| | | |
| | |cartpole-direct-link| | |
| | |cartpole-camera-rgb-link| | |
+------------------+-----------------------------+-------------------------------------------------------------------------+
| |cartpole| | |cartpole-camera-rgb-link| | Move the cart to keep the pole upwards in the classic cartpole control |
| | | and perceptive inputs |
| | |cartpole-camera-dpt-link| | |
+------------------+-----------------------------+-------------------------------------------------------------------------+
......@@ -68,26 +88,31 @@ for the reach environment:
.. table::
:widths: 33 37 30
+----------------+---------------------------+-----------------------------------------------------------------------------+
| World | Environment ID | Description |
+================+===========================+=============================================================================+
| |reach-franka| | |reach-franka-link| | Move the end-effector to a sampled target pose with the Franka robot |
+----------------+---------------------------+-----------------------------------------------------------------------------+
| |reach-ur10| | |reach-ur10-link| | Move the end-effector to a sampled target pose with the UR10 robot |
+----------------+---------------------------+-----------------------------------------------------------------------------+
| |lift-cube| | |lift-cube-link| | Pick a cube and bring it to a sampled target position with the Franka robot |
+----------------+---------------------------+-----------------------------------------------------------------------------+
| |cabi-franka| | | |cabi-franka-link| | Grasp the handle of a cabinet's drawer and open it with the Franka robot |
| | | |franka-direct-link| | |
+----------------+---------------------------+-----------------------------------------------------------------------------+
| |cube-allegro| | |cube-allegro-link| | In-hand reorientation of a cube using Allegro hand |
| | |allegro-direct-link| | |
+----------------+---------------------------+-----------------------------------------------------------------------------+
| |cube-shadow| | | |cube-shadow-link| | In-hand reorientation of a cube using Shadow hand |
| | | |cube-shadow-ff-link| | |
| | | |cube-shadow-lstm-link| | |
| | | |cube-shadow-vis-link| | |
+----------------+---------------------------+-----------------------------------------------------------------------------+
+--------------------+-------------------------+-----------------------------------------------------------------------------+
| World | Environment ID | Description |
+====================+=========================+=============================================================================+
| |reach-franka| | |reach-franka-link| | Move the end-effector to a sampled target pose with the Franka robot |
+--------------------+-------------------------+-----------------------------------------------------------------------------+
| |reach-ur10| | |reach-ur10-link| | Move the end-effector to a sampled target pose with the UR10 robot |
+--------------------+-------------------------+-----------------------------------------------------------------------------+
| |lift-cube| | |lift-cube-link| | Pick a cube and bring it to a sampled target position with the Franka robot |
+--------------------+-------------------------+-----------------------------------------------------------------------------+
| |cabi-franka| | |cabi-franka-link| | Grasp the handle of a cabinet's drawer and open it with the Franka robot |
| | | |
| | |franka-direct-link| | |
+--------------------+-------------------------+-----------------------------------------------------------------------------+
| |cube-allegro| | |cube-allegro-link| | In-hand reorientation of a cube using Allegro hand |
| | | |
| | |allegro-direct-link| | |
+--------------------+-------------------------+-----------------------------------------------------------------------------+
| |cube-shadow| | |cube-shadow-link| | In-hand reorientation of a cube using Shadow hand |
| | | |
| | |cube-shadow-ff-link| | |
| | | |
| | |cube-shadow-lstm-link| | |
+--------------------+-------------------------+-----------------------------------------------------------------------------+
| |cube-shadow| | |cube-shadow-vis-link| | In-hand reorientation of a cube using Shadow hand and perceptive inputs |
+--------------------+-------------------------+-----------------------------------------------------------------------------+
.. |reach-franka| image:: ../_static/tasks/manipulation/franka_reach.jpg
.. |reach-ur10| image:: ../_static/tasks/manipulation/ur10_reach.jpg
......@@ -127,9 +152,11 @@ Environments based on legged locomotion tasks.
| |velocity-rough-anymal-b| | |velocity-rough-anymal-b-link| | Track a velocity command on rough terrain with the Anymal B robot |
+------------------------------+----------------------------------------------+------------------------------------------------------------------------------+
| |velocity-flat-anymal-c| | |velocity-flat-anymal-c-link| | Track a velocity command on flat terrain with the Anymal C robot |
| | | |
| | |velocity-flat-anymal-c-direct-link| | |
+------------------------------+----------------------------------------------+------------------------------------------------------------------------------+
| |velocity-rough-anymal-c| | |velocity-rough-anymal-c-link| | Track a velocity command on rough terrain with the Anymal C robot |
| | | |
| | |velocity-rough-anymal-c-direct-link| | |
+------------------------------+----------------------------------------------+------------------------------------------------------------------------------+
| |velocity-flat-anymal-d| | |velocity-flat-anymal-d-link| | Track a velocity command on flat terrain with the Anymal D robot |
......
docs/source/overview/reinforcement-learning/rl_existing_scripts.rst
View file @ 06715c2c
......@@ -11,17 +11,38 @@ Stable-Baselines3
`Stable-Baselines3 <https://stable-baselines3.readthedocs.io/en/master/index.html>`__
on ``Isaac-Cartpole-v0``:
.. code:: bash
# install python module (for stable-baselines3)
./isaaclab.sh -i sb3
# run script for training
# note: we set the device to cpu since SB3 doesn't optimize for GPU anyway
./isaaclab.sh -p source/standalone/workflows/sb3/train.py --task Isaac-Cartpole-v0 --headless --device cpu
# run script for playing with 32 environments
./isaaclab.sh -p source/standalone/workflows/sb3/play.py --task Isaac-Cartpole-v0 --num_envs 32 --checkpoint /PATH/TO/model.zip
# run script for recording video of a trained agent (requires installing `ffmpeg`)
./isaaclab.sh -p source/standalone/workflows/sb3/play.py --task Isaac-Cartpole-v0 --headless --video --video_length 200
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
# install python module (for stable-baselines3)
./isaaclab.sh -i sb3
# run script for training
# note: we set the device to cpu since SB3 doesn't optimize for GPU anyway
./isaaclab.sh -p source/standalone/workflows/sb3/train.py --task Isaac-Cartpole-v0 --headless --device cpu
# run script for playing with 32 environments
./isaaclab.sh -p source/standalone/workflows/sb3/play.py --task Isaac-Cartpole-v0 --num_envs 32 --checkpoint /PATH/TO/model.zip
# run script for recording video of a trained agent (requires installing `ffmpeg`)
./isaaclab.sh -p source/standalone/workflows/sb3/play.py --task Isaac-Cartpole-v0 --headless --video --video_length 200
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
:: install python module (for stable-baselines3)
isaaclab.bat -i sb3
:: run script for training
:: note: we set the device to cpu since SB3 doesn't optimize for GPU anyway
isaaclab.bat -p source\standalone\workflows\sb3\train.py --task Isaac-Cartpole-v0 --headless --device cpu
:: run script for playing with 32 environments
isaaclab.bat -p source\standalone\workflows\sb3\play.py --task Isaac-Cartpole-v0 --num_envs 32 --checkpoint /PATH/TO/model.zip
:: run script for recording video of a trained agent (requires installing `ffmpeg`)
isaaclab.bat -p source\standalone\workflows\sb3\play.py --task Isaac-Cartpole-v0 --headless --video --video_length 200
SKRL
----
......@@ -33,16 +54,36 @@ SKRL
.. tab-item:: PyTorch
.. code:: bash
.. tab-set::
:sync-group: os
# install python module (for skrl)
./isaaclab.sh -i skrl
# run script for training
./isaaclab.sh -p source/standalone/workflows/skrl/train.py --task Isaac-Reach-Franka-v0 --headless
# run script for playing with 32 environments
./isaaclab.sh -p source/standalone/workflows/skrl/play.py --task Isaac-Reach-Franka-v0 --num_envs 32 --checkpoint /PATH/TO/model.pt
# run script for recording video of a trained agent (requires installing `ffmpeg`)
./isaaclab.sh -p source/standalone/workflows/skrl/play.py --task Isaac-Reach-Franka-v0 --headless --video --video_length 200
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
# install python module (for skrl)
./isaaclab.sh -i skrl
# run script for training
./isaaclab.sh -p source/standalone/workflows/skrl/train.py --task Isaac-Reach-Franka-v0 --headless
# run script for playing with 32 environments
./isaaclab.sh -p source/standalone/workflows/skrl/play.py --task Isaac-Reach-Franka-v0 --num_envs 32 --checkpoint /PATH/TO/model.pt
# run script for recording video of a trained agent (requires installing `ffmpeg`)
./isaaclab.sh -p source/standalone/workflows/skrl/play.py --task Isaac-Reach-Franka-v0 --headless --video --video_length 200
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
:: install python module (for skrl)
isaaclab.bat -i skrl
:: run script for training
isaaclab.bat -p source\standalone\workflows\skrl\train.py --task Isaac-Reach-Franka-v0 --headless
:: run script for playing with 32 environments
isaaclab.bat -p source\standalone\workflows\skrl\play.py --task Isaac-Reach-Franka-v0 --num_envs 32 --checkpoint /PATH/TO/model.pt
:: run script for recording video of a trained agent (requires installing `ffmpeg`)
isaaclab.bat -p source\standalone\workflows\skrl\play.py --task Isaac-Reach-Franka-v0 --headless --video --video_length 200
.. tab-item:: JAX
......@@ -61,15 +102,32 @@ SKRL
- Training the multi-agent environment ``Isaac-Shadow-Hand-Over-Direct-v0`` with skrl:
.. code:: bash
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
# install python module (for skrl)
./isaaclab.sh -i skrl
# run script for training with the MAPPO algorithm (IPPO is also supported)
./isaaclab.sh -p source/standalone/workflows/skrl/train.py --task Isaac-Shadow-Hand-Over-Direct-v0 --headless --algorithm MAPPO
# run script for playing with 32 environments with the MAPPO algorithm (IPPO is also supported)
./isaaclab.sh -p source/standalone/workflows/skrl/play.py --task Isaac-Shadow-Hand-Over-Direct-v0 --num_envs 32 --algorithm MAPPO --checkpoint /PATH/TO/model.pt
# install python module (for skrl)
./isaaclab.sh -i skrl
# run script for training with the MAPPO algorithm (IPPO is also supported)
./isaaclab.sh -p source/standalone/workflows/skrl/train.py --task Isaac-Shadow-Hand-Over-Direct-v0 --headless --algorithm MAPPO
# run script for playing with 32 environments with the MAPPO algorithm (IPPO is also supported)
./isaaclab.sh -p source/standalone/workflows/skrl/play.py --task Isaac-Shadow-Hand-Over-Direct-v0 --num_envs 32 --algorithm MAPPO --checkpoint /PATH/TO/model.pt
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
:: install python module (for skrl)
isaaclab.bat -i skrl
:: run script for training with the MAPPO algorithm (IPPO is also supported)
isaaclab.bat -p source\standalone\workflows\skrl\train.py --task Isaac-Shadow-Hand-Over-Direct-v0 --headless --algorithm MAPPO
:: run script for playing with 32 environments with the MAPPO algorithm (IPPO is also supported)
isaaclab.bat -p source\standalone\workflows\skrl\play.py --task Isaac-Shadow-Hand-Over-Direct-v0 --num_envs 32 --algorithm MAPPO --checkpoint /PATH/TO/model.pt
RL-Games
--------
......@@ -77,17 +135,36 @@ RL-Games
- Training an agent with
`RL-Games <https://github.com/Denys88/rl_games>`__ on ``Isaac-Ant-v0``:
.. code:: bash
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
# install python module (for rl-games)
./isaaclab.sh -i rl_games
# run script for training
./isaaclab.sh -p source/standalone/workflows/rl_games/train.py --task Isaac-Ant-v0 --headless
# run script for playing with 32 environments
./isaaclab.sh -p source/standalone/workflows/rl_games/play.py --task Isaac-Ant-v0 --num_envs 32 --checkpoint /PATH/TO/model.pth
# run script for recording video of a trained agent (requires installing `ffmpeg`)
./isaaclab.sh -p source/standalone/workflows/rl_games/play.py --task Isaac-Ant-v0 --headless --video --video_length 200
# install python module (for rl-games)
./isaaclab.sh -i rl_games
# run script for training
./isaaclab.sh -p source/standalone/workflows/rl_games/train.py --task Isaac-Ant-v0 --headless
# run script for playing with 32 environments
./isaaclab.sh -p source/standalone/workflows/rl_games/play.py --task Isaac-Ant-v0 --num_envs 32 --checkpoint /PATH/TO/model.pth
# run script for recording video of a trained agent (requires installing `ffmpeg`)
./isaaclab.sh -p source/standalone/workflows/rl_games/play.py --task Isaac-Ant-v0 --headless --video --video_length 200
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
:: install python module (for rl-games)
isaaclab.bat -i rl_games
:: run script for training
isaaclab.bat -p source\standalone\workflows\rl_games\train.py --task Isaac-Ant-v0 --headless
:: run script for playing with 32 environments
isaaclab.bat -p source\standalone\workflows\rl_games\play.py --task Isaac-Ant-v0 --num_envs 32 --checkpoint /PATH/TO/model.pth
:: run script for recording video of a trained agent (requires installing `ffmpeg`)
isaaclab.bat -p source\standalone\workflows\rl_games\play.py --task Isaac-Ant-v0 --headless --video --video_length 200
RSL-RL
------
......@@ -95,16 +172,36 @@ RSL-RL
- Training an agent with
`RSL-RL <https://github.com/leggedrobotics/rsl_rl>`__ on ``Isaac-Reach-Franka-v0``:
.. code:: bash
.. tab-set::
:sync-group: os
# install python module (for rsl-rl)
./isaaclab.sh -i rsl_rl
# 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 --load_run run_folder_name --checkpoint model.pt
# run script for recording video of a trained agent (requires installing `ffmpeg`)
./isaaclab.sh -p source/standalone/workflows/rsl_rl/play.py --task Isaac-Reach-Franka-v0 --headless --video --video_length 200
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
# install python module (for rsl-rl)
./isaaclab.sh -i rsl_rl
# 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 --load_run run_folder_name --checkpoint model.pt
# run script for recording video of a trained agent (requires installing `ffmpeg`)
./isaaclab.sh -p source/standalone/workflows/rsl_rl/play.py --task Isaac-Reach-Franka-v0 --headless --video --video_length 200
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
:: install python module (for rsl-rl)
isaaclab.bat -i rsl_rl
:: run script for training
isaaclab.bat -p source\standalone\workflows\rsl_rl\train.py --task Isaac-Reach-Franka-v0 --headless
:: run script for playing with 32 environments
isaaclab.bat -p source\standalone\workflows\rsl_rl\play.py --task Isaac-Reach-Franka-v0 --num_envs 32 --load_run run_folder_name --checkpoint model.pt
:: run script for recording video of a trained agent (requires installing `ffmpeg`)
isaaclab.bat -p source\standalone\workflows\rsl_rl\play.py --task Isaac-Reach-Franka-v0 --headless --video --video_length 200
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>``
......@@ -113,9 +210,23 @@ which the training script was executed.
To view the logs, run:
.. code:: bash
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
# execute from the root directory of the repository
./isaaclab.sh -p -m tensorboard.main --logdir=logs
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
# execute from the root directory of the repository
./isaaclab.sh -p -m tensorboard.main --logdir=logs
:: execute from the root directory of the repository
isaaclab.bat -p -m tensorboard.main --logdir=logs
.. _Tensorboard: https://www.tensorflow.org/tensorboard
docs/source/overview/sample_scripts.rst
View file @ 06715c2c
......@@ -10,36 +10,114 @@ A few quick showroom scripts to run and checkout:
- Spawn different quadrupeds and make robots stand using position commands:
.. code:: bash
.. tab-set::
:sync-group: os
./isaaclab.sh -p source/standalone/demos/quadrupeds.py
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
./isaaclab.sh -p source/standalone/demos/quadrupeds.py
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
isaaclab.bat -p source\standalone\demos\quadrupeds.py
- Spawn different arms and apply random joint position commands:
.. code:: bash
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
./isaaclab.sh -p source/standalone/demos/arms.py
./isaaclab.sh -p source/standalone/demos/arms.py
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
isaaclab.bat -p source\standalone\demos\arms.py
- Spawn different hands and command them to open and close:
.. code:: bash
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
./isaaclab.sh -p source/standalone/demos/hands.py
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
./isaaclab.sh -p source/standalone/demos/hands.py
isaaclab.bat -p source\standalone\demos\hands.py
- Spawn procedurally generated terrains with different configurations:
.. code:: bash
.. tab-set::
:sync-group: os
./isaaclab.sh -p source/standalone/demos/procedural_terrain.py
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
./isaaclab.sh -p source/standalone/demos/procedural_terrain.py
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
isaaclab.bat -p source\standalone\demos\procedural_terrain.py
- Spawn different deformable (soft) bodies and let them fall from a height:
.. code:: bash
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
./isaaclab.sh -p source/standalone/demos/deformables.py
./isaaclab.sh -p source/standalone/demos/deformables.py
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
isaaclab.bat -p source\standalone\demos\deformables.py
- Spawn multiple markers that are useful for visualizations:
.. code:: bash
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
./isaaclab.sh -p source/standalone/demos/markers.py
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
./isaaclab.sh -p source/standalone/demos/markers.py
isaaclab.bat -p source\standalone\demos\markers.py
docs/source/refs/additional_resources.rst 0 → 100644
View file @ 06715c2c
Additional Resources
====================
Here we provide external links to tools and various resources that you may also find useful.
Sim-to-Real Resources
---------------------
One of the core goals of the broader Isaac project is to bring real robots to life through the power of NVIDIA technology. There are many ways to do this, and thus, many tools that you could use. These resources are dedicated to helping you navigate these possibilities by providing examples and discussions about closing the Sim-to-Real gap and deploying policies to actual real robots.
* `Closing the Sim-to-Real Gap: Training Spot Quadruped Locomotion with NVIDIA Isaac Lab <https://developer.nvidia.com/blog/closing-the-sim-to-real-gap-training-spot-quadruped-locomotion-with-nvidia-isaac-lab/>`_ is a detailed guide for training a quadruped locomotion policy for the Spot Quadruped from Boston Dynamics, and deploying it to the real robot.
LLM Generated Reward Functions
------------------------------
Our research endeavor, ``Eureka!``, has resulted in a pipeline for generating and tuning Reinforcement Learning (RL) reward functions using an LLM. These resources are dedicated to helping you utilize this pipeline to create RL based solutions to tasks that were once thought impossible!
* `Isaac Lab Eureka <https://github.com/isaac-sim/IsaacLabEureka>`_ is a github repository where you can setup your own LLM reward generation pipeline for your direct RL environments built in Isaac Lab!
* `Eureka! NVIDIA Research Breakthrough Puts New Spin on Robot Learning <https://blogs.nvidia.com/blog/eureka-robotics-research/>`_ is a blog post that covers the broad idea of this reward generation process.
Simulation Features
-------------------
At the heart of Isaac Lab is Isaac Sim, which is itself a feature rich tool that is useful for robotics in general, and not only for RL. The stronger your understanding of the simulation, the readily you will be able to exploit its capabilities for your own projects and applications. These resources are dedicated to informing you about the other features of the simulation that may be useful to you given your specific interest in Isaac Lab!
* `Deploying Policies in Isaac Sim <https://docs.omniverse.nvidia.com/isaacsim/latest/isaac_lab_tutorials/tutorial_policy_deployment.html>`_ is an Isaac Sim tutorial on how to use trained policies within the simulation.
* `Supercharge Robotics Workflows with AI and Simulation Using NVIDIA Isaac Sim 4.0 and NVIDIA Isaac Lab <https://developer.nvidia.com/blog/supercharge-robotics-workflows-with-ai-and-simulation-using-nvidia-isaac-sim-4-0-and-nvidia-isaac-lab/>`_ is a blog post covering the newest features of Isaac Sim 4.0, including ``pip install``, a more advanced physics engine, updated sensor simulations, and more!
* `Fast-Track Robot Learning in Simulation Using NVIDIA Isaac Lab <https://developer.nvidia.com/blog/fast-track-robot-learning-in-simulation-using-nvidia-isaac-lab/>`_ is a blog post covering the gamut of features for accelerated robot learning through Isaac Lab.
docs/source/setup/installation/binaries_installation.rst
View file @ 06715c2c
......@@ -4,6 +4,9 @@
Installation using Isaac Sim Binaries
=====================================
.. note::
If you use Conda, we recommend using `Miniconda <https://docs.anaconda.com/miniconda/miniconda-other-installer-links/>`_.
Installing Isaac Sim
--------------------
......@@ -35,7 +38,117 @@ To check the minimum system requirements,refer to the documentation
:sync: windows
On Windows systems, by default,Isaac Sim is installed in the directory
``C:\Users\user\AppData\Local\ov\pkg\isaac_sim-*``, with ``*`` corresponding to the Isaac Sim version.
``C:\Users\%USERPROFILE%\AppData\Local\ov\pkg\isaac_sim-*``, with ``*`` corresponding to the Isaac Sim version.
Verifying the Isaac Sim installation
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
To avoid the overhead of finding and locating the Isaac Sim installation
directory every time, we recommend exporting the following environment
variables to your terminal for the remaining of the installation instructions:
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
# Isaac Sim root directory
export ISAACSIM_PATH="${HOME}/.local/share/ov/pkg/isaac-sim-4.2.0"
# Isaac Sim python executable
export ISAACSIM_PYTHON_EXE="${ISAACSIM_PATH}/python.sh"
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
:: Isaac Sim root directory
set ISAACSIM_PATH="C:\Users\%USERPROFILE%\AppData\Local\ov\pkg\isaac-sim-4.2.0"
:: Isaac Sim python executable
set ISAACSIM_PYTHON_EXE="%ISAACSIM_PATH:"=%\python.bat"
For more information on common paths, please check the Isaac Sim
`documentation <https://docs.omniverse.nvidia.com/isaacsim/latest/installation/install_faq.html#common-path-locations>`__.
- Check that the simulator runs as expected:
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
# note: you can pass the argument "--help" to see all arguments possible.
${ISAACSIM_PATH}/isaac-sim.sh
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
:: note: you can pass the argument "--help" to see all arguments possible.
%ISAACSIM_PATH%\isaac-sim.bat
- Check that the simulator runs from a standalone python script:
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
# checks that python path is set correctly
${ISAACSIM_PYTHON_EXE} -c "print('Isaac Sim configuration is now complete.')"
# checks that Isaac Sim can be launched from python
${ISAACSIM_PYTHON_EXE} ${ISAACSIM_PATH}/standalone_examples/api/omni.isaac.core/add_cubes.py
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
:: checks that python path is set correctly
%ISAACSIM_PYTHON_EXE% -c "print('Isaac Sim configuration is now complete.')"
:: checks that Isaac Sim can be launched from python
%ISAACSIM_PYTHON_EXE% %ISAACSIM_PATH%\standalone_examples\api\omni.isaac.core\add_cubes.py
.. caution::
If you have been using a previous version of Isaac Sim, you need to run the following command for the *first*
time after installation to remove all the old user data and cached variables:
.. tab-set::
.. tab-item:: :icon:`fa-brands fa-linux` Linux
.. code:: bash
${ISAACSIM_PATH}/isaac-sim.sh --reset-user
.. tab-item:: :icon:`fa-brands fa-windows` Windows
.. code:: batch
%ISAACSIM_PATH%\isaac-sim.bat --reset-user
If the simulator does not run or crashes while following the above
instructions, it means that something is incorrectly configured. To
debug and troubleshoot, please check Isaac Sim
`documentation <https://docs.omniverse.nvidia.com/dev-guide/latest/linux-troubleshooting.html>`__
and the
`forums <https://docs.omniverse.nvidia.com/isaacsim/latest/isaac_sim_forums.html>`__.
Installing Isaac Lab
......@@ -258,3 +371,44 @@ Installation
isaaclab.bat --install rl_games :: or "isaaclab.bat -i rl_games"
The valid options are ``rl_games``, ``rsl_rl``, ``sb3``, ``skrl``, ``robomimic``, ``none``.
Verifying the Isaac Lab installation
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
To verify that the installation was successful, run the following command from the
top of the repository:
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
# Option 1: Using the isaaclab.sh executable
# note: this works for both the bundled python and the virtual environment
./isaaclab.sh -p source/standalone/tutorials/00_sim/create_empty.py
# Option 2: Using python in your virtual environment
python source/standalone/tutorials/00_sim/create_empty.py
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
:: Option 1: Using the isaaclab.bat executable
:: note: this works for both the bundled python and the virtual environment
isaaclab.bat -p source\standalone\tutorials\00_sim\create_empty.py
:: Option 2: Using python in your virtual environment
python source\standalone\tutorials\00_sim\create_empty.py
The above command should launch the simulator and display a window with a black
ground plane. You can exit the script by pressing ``Ctrl+C`` on your terminal.
On Windows machines, please terminate the process from Command Prompt using
``Ctrl+Break`` or ``Ctrl+fn+B``.
If you see this, then the installation was successful! |:tada:|
docs/source/setup/installation/index.rst
View file @ 06715c2c
......@@ -39,7 +39,6 @@ the launcher. Therefore, there are two ways to install Isaac Lab:
.. toctree::
:maxdepth: 2
Installation using Isaac Sim pip (experimental) <pip_installation>
binaries_installation
verifying_installation
Option 1: Installation using Isaac Sim pip <pip_installation>
Option 2: Installation using Isaac Sim binaries <binaries_installation>
cloud_installation
docs/source/setup/installation/pip_installation.rst
View file @ 06715c2c
......@@ -3,6 +3,9 @@
Installation using Isaac Sim pip
================================
.. note::
If you use Conda, we recommend using `Miniconda <https://docs.anaconda.com/miniconda/miniconda-other-installer-links/>`_.
Installing Isaac Sim
--------------------
......@@ -92,6 +95,55 @@ compatibility issues with some Linux distributions. If you encounter any issues,
pip install isaacsim-rl isaacsim-replicator isaacsim-extscache-physics isaacsim-extscache-kit-sdk isaacsim-extscache-kit isaacsim-app --extra-index-url https://pypi.nvidia.com
Verifying the Isaac Sim installation
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Make sure that your virtual environment is activated (if applicable)
- Check that the simulator runs as expected:
.. code:: bash
# note: you can pass the argument "--help" to see all arguments possible.
isaacsim
By default, this will launch an empty mini Kit window.
- To run with a specific experience file, run:
.. code:: bash
# experience files can be absolute path, or relative path searched in isaacsim/apps or omni/apps
isaacsim omni.isaac.sim.python.kit
.. attention::
When running Isaac Sim for the first time, all dependent extensions will be pulled from the registry.
This process can take upwards of 10 minutes and is required on the first run of each experience file.
Once the extensions are pulled, consecutive runs using the same experience file will use the cached extensions.
In addition, the first run will prompt users to accept the Nvidia Omniverse License Agreement.
To accept the EULA, reply ``Yes`` when prompted with the below message:
.. code:: bash
By installing or using Isaac Sim, I agree to the terms of NVIDIA OMNIVERSE LICENSE AGREEMENT (EULA)
in https://docs.omniverse.nvidia.com/isaacsim/latest/common/NVIDIA_Omniverse_License_Agreement.html
Do you accept the EULA? (Yes/No): Yes
If the simulator does not run or crashes while following the above
instructions, it means that something is incorrectly configured. To
debug and troubleshoot, please check Isaac Sim
`documentation <https://docs.omniverse.nvidia.com/dev-guide/latest/linux-troubleshooting.html>`__
and the
`forums <https://docs.omniverse.nvidia.com/isaacsim/latest/isaac_sim_forums.html>`__.
Installing Isaac Lab
--------------------
......@@ -222,3 +274,44 @@ Installation
isaaclab.bat --install rl_games :: or "isaaclab.bat -i rl_games"
The valid options are ``rl_games``, ``rsl_rl``, ``sb3``, ``skrl``, ``robomimic``, ``none``.
Verifying the Isaac Lab installation
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
To verify that the installation was successful, run the following command from the
top of the repository:
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
# Option 1: Using the isaaclab.sh executable
# note: this works for both the bundled python and the virtual environment
./isaaclab.sh -p source/standalone/tutorials/00_sim/create_empty.py
# Option 2: Using python in your virtual environment
python source/standalone/tutorials/00_sim/create_empty.py
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
:: Option 1: Using the isaaclab.bat executable
:: note: this works for both the bundled python and the virtual environment
isaaclab.bat -p source\standalone\tutorials\00_sim\create_empty.py
:: Option 2: Using python in your virtual environment
python source\standalone\tutorials\00_sim\create_empty.py
The above command should launch the simulator and display a window with a black
ground plane. You can exit the script by pressing ``Ctrl+C`` on your terminal.
On Windows machines, please terminate the process from Command Prompt using
``Ctrl+Break`` or ``Ctrl+fn+B``.
If you see this, then the installation was successful! |:tada:|
docs/source/setup/installation/verifying_installation.rst deleted 100644 → 0
View file @ 4f8b2b57
Verifying the Installation
==========================
Verifying the Isaac Sim installation
------------------------------------
Isaac Sim installed from pip
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- Make sure that your virtual environment is activated (if applicable)
- Check that the simulator runs as expected:
.. code:: bash
# note: you can pass the argument "--help" to see all arguments possible.
isaacsim
By default, this will launch an empty mini Kit window.
- To run with a specific experience file, run:
.. code:: bash
# experience files can be absolute path, or relative path searched in isaacsim/apps or omni/apps
isaacsim omni.isaac.sim.python.kit
.. attention::
When running Isaac Sim for the first time, all dependent extensions will be pulled from the registry.
This process can take upwards of 10 minutes and is required on the first run of each experience file.
Once the extensions are pulled, consecutive runs using the same experience file will use the cached extensions.
In addition, the first run will prompt users to accept the Nvidia Omniverse License Agreement.
To accept the EULA, reply ``Yes`` when prompted with the below message:
.. code:: bash
By installing or using Isaac Sim, I agree to the terms of NVIDIA OMNIVERSE LICENSE AGREEMENT (EULA)
in https://docs.omniverse.nvidia.com/isaacsim/latest/common/NVIDIA_Omniverse_License_Agreement.html
Do you accept the EULA? (Yes/No): Yes
If the simulator does not run or crashes while following the above
instructions, it means that something is incorrectly configured. To
debug and troubleshoot, please check Isaac Sim
`documentation <https://docs.omniverse.nvidia.com/dev-guide/latest/linux-troubleshooting.html>`__
and the
`forums <https://docs.omniverse.nvidia.com/isaacsim/latest/isaac_sim_forums.html>`__.
Isaac Sim installed from binaries
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
To avoid the overhead of finding and locating the Isaac Sim installation
directory every time, we recommend exporting the following environment
variables to your terminal for the remaining of the installation instructions:
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
# Isaac Sim root directory
export ISAACSIM_PATH="${HOME}/.local/share/ov/pkg/isaac-sim-4.2.0"
# Isaac Sim python executable
export ISAACSIM_PYTHON_EXE="${ISAACSIM_PATH}/python.sh"
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
:: Isaac Sim root directory
set ISAACSIM_PATH="C:\Users\user\AppData\Local\ov\pkg\isaac-sim-4.2.0"
:: Isaac Sim python executable
set ISAACSIM_PYTHON_EXE="%ISAACSIM_PATH:"=%\python.bat"
For more information on common paths, please check the Isaac Sim
`documentation <https://docs.omniverse.nvidia.com/isaacsim/latest/installation/install_faq.html#common-path-locations>`__.
- Check that the simulator runs as expected:
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
# note: you can pass the argument "--help" to see all arguments possible.
${ISAACSIM_PATH}/isaac-sim.sh
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
:: note: you can pass the argument "--help" to see all arguments possible.
%ISAACSIM_PATH%\isaac-sim.bat
- Check that the simulator runs from a standalone python script:
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
# checks that python path is set correctly
${ISAACSIM_PYTHON_EXE} -c "print('Isaac Sim configuration is now complete.')"
# checks that Isaac Sim can be launched from python
${ISAACSIM_PYTHON_EXE} ${ISAACSIM_PATH}/standalone_examples/api/omni.isaac.core/add_cubes.py
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
:: checks that python path is set correctly
%ISAACSIM_PYTHON_EXE% -c "print('Isaac Sim configuration is now complete.')"
:: checks that Isaac Sim can be launched from python
%ISAACSIM_PYTHON_EXE% %ISAACSIM_PATH%\standalone_examples\api\omni.isaac.core\add_cubes.py
.. caution::
If you have been using a previous version of Isaac Sim, you need to run the following command for the *first*
time after installation to remove all the old user data and cached variables:
.. tab-set::
.. tab-item:: :icon:`fa-brands fa-linux` Linux
.. code:: bash
${ISAACSIM_PATH}/isaac-sim.sh --reset-user
.. tab-item:: :icon:`fa-brands fa-windows` Windows
.. code:: batch
%ISAACSIM_PATH%\isaac-sim.bat --reset-user
If the simulator does not run or crashes while following the above
instructions, it means that something is incorrectly configured. To
debug and troubleshoot, please check Isaac Sim
`documentation <https://docs.omniverse.nvidia.com/dev-guide/latest/linux-troubleshooting.html>`__
and the
`forums <https://docs.omniverse.nvidia.com/isaacsim/latest/isaac_sim_forums.html>`__.
Verifying the Isaac Lab installation
------------------------------------
To verify that the installation was successful, run the following command from the
top of the repository:
.. tab-set::
:sync-group: os
.. tab-item:: :icon:`fa-brands fa-linux` Linux
:sync: linux
.. code:: bash
# Option 1: Using the isaaclab.sh executable
# note: this works for both the bundled python and the virtual environment
./isaaclab.sh -p source/standalone/tutorials/00_sim/create_empty.py
# Option 2: Using python in your virtual environment
python source/standalone/tutorials/00_sim/create_empty.py
.. tab-item:: :icon:`fa-brands fa-windows` Windows
:sync: windows
.. code:: batch
:: Option 1: Using the isaaclab.bat executable
:: note: this works for both the bundled python and the virtual environment
isaaclab.bat -p source\standalone\tutorials\00_sim\create_empty.py
:: Option 2: Using python in your virtual environment
python source\standalone\tutorials\00_sim\create_empty.py
The above command should launch the simulator and display a window with a black
ground plane. You can exit the script by pressing ``Ctrl+C`` on your terminal.
On Windows machines, please terminate the process from Command Prompt using
``Ctrl+Break`` or ``Ctrl+fn+B``.
If you see this, then the installation was successful! |:tada:|
docs/source/tutorials/00_sim/index.rst deleted 100644 → 0
View file @ 4f8b2b57
Setting up a Simple Simulation
==============================
These tutorials show you how to launch the simulation with different settings and spawn objects in the
simulated scene. They cover the following APIs: :class:`~omni.isaac.lab.app.AppLauncher`,
:class:`~omni.isaac.lab.sim.SimulationContext`, and :class:`~omni.isaac.lab.sim.spawners`.
.. toctree::
:maxdepth: 1
:titlesonly:
create_empty
spawn_prims
launch_app
docs/source/tutorials/01_assets/index.rst deleted 100644 → 0
View file @ 4f8b2b57
Interacting with Assets
=======================
Having spawned objects in the scene, these tutorials show you how to create physics handles for these
objects and interact with them. These revolve around the :class:`~omni.isaac.lab.assets.AssetBase`
class and its derivatives such as :class:`~omni.isaac.lab.assets.RigidObject`,
:class:`~omni.isaac.lab.assets.Articulation` and :class:`~omni.isaac.lab.assets.DeformableObject`.
.. toctree::
:maxdepth: 1
:titlesonly:
run_rigid_object
run_articulation
run_deformable_object
docs/source/tutorials/01_assets/run_articulation.rst
View file @ 06715c2c
......@@ -82,7 +82,7 @@ Applying commands to the articulation involves two steps:
1. *Setting the joint targets*: This sets the desired joint position, velocity, or effort targets for the articulation.
2. *Writing the data to the simulation*: Based on the articulation's configuration, this step handles any
:ref:`actuation conversions <feature-actuators>` and writes the converted values to the PhysX buffer.
:ref:`actuation conversions <overview-actuators>` and writes the converted values to the PhysX buffer.
In this tutorial, we control the articulation using joint effort commands. For this to work, we need to set the
articulation's stiffness and damping parameters to zero. This is done a-priori inside the cart-pole's pre-defined
......
docs/source/tutorials/02_scene/index.rst deleted 100644 → 0
View file @ 4f8b2b57
Creating a Scene
================
With the basic concepts of the framework covered, the tutorials move to a more intuitive scene
interface that uses the :class:`~omni.isaac.lab.scene.InteractiveScene` class. This class
provides a higher level abstraction for creating scenes easily.
.. toctree::
:maxdepth: 1
:titlesonly:
create_scene
docs/source/tutorials/03_envs/index.rst deleted 100644 → 0
View file @ 4f8b2b57
Designing an Environment
========================
The following tutorials introduce the concept of manager-based environments: :class:`~omni.isaac.lab.envs.ManagerBasedEnv`
and its derivative :class:`~omni.isaac.lab.envs.ManagerBasedRLEnv`, as well as the direct workflow base class
:class:`~omni.isaac.lab.envs.DirectRLEnv`. These environments bring-in together
different aspects of the framework to create a simulation environment for agent interaction.
.. toctree::
:maxdepth: 1
:titlesonly:
create_manager_base_env
create_manager_rl_env
create_direct_rl_env
register_rl_env_gym
run_rl_training
modify_direct_rl_env
docs/source/tutorials/04_sensors/index.rst deleted 100644 → 0
View file @ 4f8b2b57
Integrating Sensors
===================
The following tutorial shows you how to integrate sensors into the simulation environment. The
tutorials introduce the :class:`~omni.isaac.lab.sensors.SensorBase` class and its derivatives
such as :class:`~omni.isaac.lab.sensors.Camera` and :class:`~omni.isaac.lab.sensors.RayCaster`.
.. toctree::
:maxdepth: 1
:titlesonly:
add_sensors_on_robot
docs/source/tutorials/05_controllers/index.rst deleted 100644 → 0
View file @ 4f8b2b57
Using Motion Generators
=======================
While the robots in the simulation environment can be controlled at the joint-level, the following
tutorials show you how to use motion generators to control the robots at the task-level.
.. toctree::
:maxdepth: 1
:titlesonly:
run_diff_ik
docs/source/tutorials/index.rst
View file @ 06715c2c
......@@ -13,12 +13,91 @@ repository.
We recommend that you go through the tutorials in the order they are listed here.
Setting up a Simple Simulation
-------------------------------
These tutorials show you how to launch the simulation with different settings and spawn objects in the
simulated scene. They cover the following APIs: :class:`~omni.isaac.lab.app.AppLauncher`,
:class:`~omni.isaac.lab.sim.SimulationContext`, and :class:`~omni.isaac.lab.sim.spawners`.
.. toctree::
:maxdepth: 1
:titlesonly:
00_sim/create_empty
00_sim/spawn_prims
00_sim/launch_app
Interacting with Assets
-----------------------
Having spawned objects in the scene, these tutorials show you how to create physics handles for these
objects and interact with them. These revolve around the :class:`~omni.isaac.lab.assets.AssetBase`
class and its derivatives such as :class:`~omni.isaac.lab.assets.RigidObject`,
:class:`~omni.isaac.lab.assets.Articulation` and :class:`~omni.isaac.lab.assets.DeformableObject`.
.. toctree::
:maxdepth: 2
00_sim/index
01_assets/index
02_scene/index
03_envs/index
04_sensors/index
05_controllers/index
:maxdepth: 1
:titlesonly:
01_assets/run_rigid_object
01_assets/run_articulation
01_assets/run_deformable_object
Creating a Scene
----------------
With the basic concepts of the framework covered, the tutorials move to a more intuitive scene
interface that uses the :class:`~omni.isaac.lab.scene.InteractiveScene` class. This class
provides a higher level abstraction for creating scenes easily.
.. toctree::
:maxdepth: 1
:titlesonly:
02_scene/create_scene
Designing an Environment
------------------------
The following tutorials introduce the concept of manager-based environments: :class:`~omni.isaac.lab.envs.ManagerBasedEnv`
and its derivative :class:`~omni.isaac.lab.envs.ManagerBasedRLEnv`, as well as the direct workflow base class
:class:`~omni.isaac.lab.envs.DirectRLEnv`. These environments bring-in together
different aspects of the framework to create a simulation environment for agent interaction.
.. toctree::
:maxdepth: 1
:titlesonly:
03_envs/create_manager_base_env
03_envs/create_manager_rl_env
03_envs/create_direct_rl_env
03_envs/register_rl_env_gym
03_envs/run_rl_training
03_envs/modify_direct_rl_env
Integrating Sensors
-------------------
The following tutorial shows you how to integrate sensors into the simulation environment. The
tutorials introduce the :class:`~omni.isaac.lab.sensors.SensorBase` class and its derivatives
such as :class:`~omni.isaac.lab.sensors.Camera` and :class:`~omni.isaac.lab.sensors.RayCaster`.
.. toctree::
:maxdepth: 1
:titlesonly:
04_sensors/add_sensors_on_robot
Using motion generators
-----------------------
While the robots in the simulation environment can be controlled at the joint-level, the following
tutorials show you how to use motion generators to control the robots at the task-level.
.. toctree::
:maxdepth: 1
:titlesonly:
05_controllers/run_diff_ik
source/apps/isaaclab.python.headless.rendering.kit
View file @ 06715c2c
......@@ -124,8 +124,3 @@ folders = [
"${app}", # needed to find other app files
"${app}/../extensions", # needed to find extensions in Isaac Lab
]
# Isaac Sim Extensions
###############################
[dependencies]
#"omni.isaac.app.setup" = { order = 1000 } # we are running that at the end
source/apps/isaaclab.python.rendering.kit
View file @ 06715c2c
......@@ -121,8 +121,3 @@ folders = [
"${app}", # needed to find other app files
"${app}/../extensions", # needed to find extensions in Isaac Lab
]
# Isaac Sim Extensions
###############################
[dependencies]
"omni.isaac.app.setup" = { order = 1000 } # we are running that at the end
source/extensions/omni.isaac.lab/config/extension.toml
View file @ 06715c2c
[package]
# Note: Semantic Versioning is used: https://semver.org/
version = "0.24.12"
version = "0.24.13"
# Description
title = "Isaac Lab framework for Robot Learning"
......
source/extensions/omni.isaac.lab/docs/CHANGELOG.rst
View file @ 06715c2c
......@@ -2,6 +2,16 @@ Changelog
---------
0.24.13 (2024-09-08)
~~~~~~~~~~~~~~~~~~~~
Changed
^^^^^^^
* Moved the configuration of visualization markers for the command terms to their respective configuration classes.
This allows users to modify the markers for the command terms without having to modify the command term classes.
0.24.12 (2024-09-18)
~~~~~~~~~~~~~~~~~~~~
......
source/extensions/omni.isaac.lab/omni/isaac/lab/sim/schemas/schemas.py
View file @ 06715c2c
......@@ -84,7 +84,7 @@ def modify_articulation_root_properties(
This function is decorated with :func:`apply_nested` that set the properties to all the prims
(that have the schema applied on them) under the input prim path.
.. _articulation root: https://nvidia-omniverse.github.io/PhysX/physx/5.4.0/docs/Articulations.html
.. _articulation root: https://nvidia-omniverse.github.io/PhysX/physx/5.4.1/docs/Articulations.html
.. _ArticulationRootAPI: https://openusd.org/dev/api/class_usd_physics_articulation_root_a_p_i.html
.. _PhysxArticulationAPI: https://docs.omniverse.nvidia.com/kit/docs/omni_usd_schema_physics/104.2/class_physx_schema_physx_articulation_a_p_i.html
......@@ -234,7 +234,7 @@ def modify_rigid_body_properties(
This function is decorated with :func:`apply_nested` that sets the properties to all the prims
(that have the schema applied on them) under the input prim path.
.. _rigid body: https://nvidia-omniverse.github.io/PhysX/physx/5.4.0/docs/RigidBodyOverview.html
.. _rigid body: https://nvidia-omniverse.github.io/PhysX/physx/5.4.1/docs/RigidBodyOverview.html
.. _kinematic body: https://openusd.org/release/wp_rigid_body_physics.html#kinematic-bodies
.. _RigidBodyAPI: https://openusd.org/dev/api/class_usd_physics_rigid_body_a_p_i.html
.. _PhysxRigidBodyAPI: https://docs.omniverse.nvidia.com/kit/docs/omni_usd_schema_physics/104.2/class_physx_schema_physx_rigid_body_a_p_i.html
......@@ -323,7 +323,7 @@ def modify_collision_properties(
Tuning these parameters influence the contact behavior of the rigid body. For more information on
tune them and their effect on the simulation, please refer to the
`PhysX documentation <https://nvidia-omniverse.github.io/PhysX/physx/5.4.0/docs/AdvancedCollisionDetection.html>`__.
`PhysX documentation <https://nvidia-omniverse.github.io/PhysX/physx/5.4.1/docs/AdvancedCollisionDetection.html>`__.
.. note::
This function is decorated with :func:`apply_nested` that sets the properties to all the prims
......@@ -616,7 +616,7 @@ def modify_fixed_tendon_properties(
This function is decorated with :func:`apply_nested` that sets the properties to all the prims
(that have the schema applied on them) under the input prim path.
.. _fixed tendon: https://nvidia-omniverse.github.io/PhysX/physx/5.3.1/_api_build/class_px_articulation_fixed_tendon.html
.. _fixed tendon: https://nvidia-omniverse.github.io/PhysX/physx/5.4.1/_api_build/classPxArticulationFixedTendon.html
.. _PhysxTendonAxisRootAPI: https://docs.omniverse.nvidia.com/kit/docs/omni_usd_schema_physics/104.2/class_physx_schema_physx_tendon_axis_root_a_p_i.html
Args:
......@@ -749,7 +749,7 @@ def modify_deformable_body_properties(
This function is decorated with :func:`apply_nested` that sets the properties to all the prims
(that have the schema applied on them) under the input prim path.
.. _deformable body: https://nvidia-omniverse.github.io/PhysX/physx/5.4.0/docs/SoftBodies.html
.. _deformable body: https://nvidia-omniverse.github.io/PhysX/physx/5.4.1/docs/SoftBodies.html
.. _PhysxDeformableBodyAPI: https://docs.omniverse.nvidia.com/kit/docs/omni_usd_schema_physics/104.2/class_physx_schema_physx_deformable_a_p_i.html
Args:
......
source/extensions/omni.isaac.lab/omni/isaac/lab/sim/schemas/schemas_cfg.py
View file @ 06715c2c
......@@ -267,7 +267,7 @@ class DeformableBodyPropertiesCfg:
"""Enables kinematic body. Defaults to False, which means that the body is not kinematic.
Similar to rigid bodies, this allows setting user-driven motion for the deformable body. For more information,
please refer to the `documentation <https://nvidia-omniverse.github.io/PhysX/physx/5.4.0/docs/SoftBodies.html#kinematic-soft-bodies>`__.
please refer to the `documentation <https://nvidia-omniverse.github.io/PhysX/physx/5.4.1/docs/SoftBodies.html#kinematic-soft-bodies>`__.
"""
self_collision: bool | None = None
......
source/extensions/omni.isaac.lab/omni/isaac/lab/sim/simulation_cfg.py
View file @ 06715c2c
......@@ -30,7 +30,7 @@ class PhysxCfg:
simulation will fail with errors and lead to adverse behaviors. The buffer sizes can be adjusted through the
``gpu_*`` parameters.
.. _PhysX 5 SDK documentation: https://nvidia-omniverse.github.io/PhysX/physx/5.3.1/_api_build/class_px_scene_desc.html
.. _PhysX 5 SDK documentation: https://nvidia-omniverse.github.io/PhysX/physx/5.4.1/_api_build/classPxSceneDesc.html
"""
......@@ -95,7 +95,7 @@ class PhysxCfg:
For more information on PhysX determinism, please check `here`_.
.. _here: https://nvidia-omniverse.github.io/PhysX/physx/5.3.1/docs/RigidBodyDynamics.html#enhanced-determinism
.. _here: https://nvidia-omniverse.github.io/PhysX/physx/5.4.1/docs/RigidBodyDynamics.html#enhanced-determinism
"""
bounce_threshold_velocity: float = 0.5
......
source/extensions/omni.isaac.lab/omni/isaac/lab/sim/simulation_context.py
View file @ 06715c2c
......@@ -133,7 +133,7 @@ class SimulationContext(_SimulationContext):
carb_settings_iface.set_bool("/physics/disableContactProcessing", True)
# enable custom geometry for cylinder and cone collision shapes to allow contact reporting for them
# reason: cylinders and cones aren't natively supported by PhysX so we need to use custom geometry flags
# reference: https://nvidia-omniverse.github.io/PhysX/physx/5.4.0/docs/Geometry.html?highlight=capsule#geometry
# reference: https://nvidia-omniverse.github.io/PhysX/physx/5.4.1/docs/Geometry.html?highlight=capsule#geometry
carb_settings_iface.set_bool("/physics/collisionConeCustomGeometry", False)
carb_settings_iface.set_bool("/physics/collisionCylinderCustomGeometry", False)
# note: we read this once since it is not expected to change during runtime
......@@ -535,7 +535,7 @@ class SimulationContext(_SimulationContext):
raise RuntimeError("Physics scene API is None! Please create the scene first.")
# set parameters not directly supported by the constructor
# -- Continuous Collision Detection (CCD)
# ref: https://nvidia-omniverse.github.io/PhysX/physx/5.4.0/docs/AdvancedCollisionDetection.html?highlight=ccd#continuous-collision-detection
# ref: https://nvidia-omniverse.github.io/PhysX/physx/5.4.1/docs/AdvancedCollisionDetection.html?highlight=ccd#continuous-collision-detection
self._physics_context.enable_ccd(self.cfg.physx.enable_ccd)
# -- GPU collision stack size
physx_scene_api.CreateGpuCollisionStackSizeAttr(self.cfg.physx.gpu_collision_stack_size)
......
source/extensions/omni.isaac.lab/omni/isaac/lab/sim/spawners/materials/physics_materials.py
View file @ 06715c2c
......@@ -23,7 +23,7 @@ def spawn_rigid_body_material(prim_path: str, cfg: physics_materials_cfg.RigidBo
Rigid body materials are used to define the physical properties to meshes of a rigid body. These
include the friction, restitution, and their respective combination modes. For more information on
rigid body material, please refer to the `documentation on PxMaterial <https://nvidia-omniverse.github.io/PhysX/physx/5.4.0/_build/physx/latest/class_px_material.html>`_.
rigid body material, please refer to the `documentation on PxMaterial <https://nvidia-omniverse.github.io/PhysX/physx/5.4.1/_api_build/classPxBaseMaterial.html>`_.
.. note::
This function is decorated with :func:`clone` that resolves prim path into list of paths
......@@ -97,7 +97,7 @@ def spawn_deformable_body_material(prim_path: str, cfg: physics_materials_cfg.De
Raises:
ValueError: When a prim already exists at the specified prim path and is not a material.
.. _PxFEMSoftBodyMaterial: https://nvidia-omniverse.github.io/PhysX/physx/5.4.0/_api_build/class_px_f_e_m_soft_body_material.html
.. _PxFEMSoftBodyMaterial: https://nvidia-omniverse.github.io/PhysX/physx/5.4.1/_api_build/structPxFEMSoftBodyMaterialModel.html
"""
# create material prim if no prim exists
if not prim_utils.is_prim_path_valid(prim_path):
......
source/extensions/omni.isaac.lab/omni/isaac/lab/sim/spawners/materials/physics_materials_cfg.py
View file @ 06715c2c
......@@ -19,7 +19,7 @@ class PhysicsMaterialCfg:
Physics material are PhysX schemas that can be applied to a USD material prim to define the
physical properties related to the material. For example, the friction coefficient, restitution
coefficient, etc. For more information on physics material, please refer to the
`PhysX documentation <https://nvidia-omniverse.github.io/PhysX/physx/5.4.0/_build/physx/latest/class_px_base_material.html>`__.
`PhysX documentation <https://nvidia-omniverse.github.io/PhysX/physx/5.4.1/_api_build/classPxBaseMaterial.html>`__.
"""
func: Callable = MISSING
......@@ -58,7 +58,7 @@ class RigidBodyMaterialCfg(PhysicsMaterialCfg):
When two physics materials with different combine modes collide, the combine mode with the higher
priority will be used. The priority order is provided `here
<https://nvidia-omniverse.github.io/PhysX/physx/5.4.0/_build/physx/latest/struct_px_combine_mode.html#pxcombinemode>`__.
<https://nvidia-omniverse.github.io/PhysX/physx/5.4.1/_api_build/structPxCombineMode.html>`__.
"""
restitution_combine_mode: Literal["average", "min", "multiply", "max"] = "average"
......@@ -68,7 +68,7 @@ class RigidBodyMaterialCfg(PhysicsMaterialCfg):
When two physics materials with different combine modes collide, the combine mode with the higher
priority will be used. The priority order is provided `here
<https://nvidia-omniverse.github.io/PhysX/physx/5.4.0/_build/physx/latest/struct_px_combine_mode.html#pxcombinemode>`__.
<https://nvidia-omniverse.github.io/PhysX/physx/5.4.1/_api_build/structPxCombineMode.html>`__.
"""
compliant_contact_stiffness: float = 0.0
......
source/extensions/omni.isaac.lab_tasks/omni/isaac/lab_tasks/direct/shadow_hand/feature_extractor.py
View file @ 06715c2c
......@@ -170,7 +170,7 @@ class FeatureExtractor:
img_input = torch.cat((rgb_img, depth_img, segmentation_img), dim=-1)
self.optimizer.zero_grad()
predicted_pose = self.feature_extractor(img_input).squeeze()
predicted_pose = self.feature_extractor(img_input)
pose_loss = self.l2_loss(predicted_pose, gt_pose.clone()) * 100
pose_loss.backward()
......@@ -187,5 +187,5 @@ class FeatureExtractor:
return pose_loss, predicted_pose
else:
img_input = torch.cat((rgb_img, depth_img, segmentation_img), dim=-1)
predicted_pose = self.feature_extractor(img_input).squeeze()
predicted_pose = self.feature_extractor(img_input)
return None, predicted_pose
source/extensions/omni.isaac.lab_tasks/omni/isaac/lab_tasks/direct/shadow_hand/shadow_hand_vision_env.py
View file @ 06715c2c
......@@ -90,9 +90,6 @@ class ShadowHandVisionEnv(InHandManipulationEnv):
# add lights
light_cfg = sim_utils.DomeLightCfg(intensity=2000.0, color=(0.75, 0.75, 0.75))
light_cfg.func("/World/Light", light_cfg)
# hide default lights when running with viewer
if stage.GetPrimAtPath("/Environment/defaultLight"):
stage.GetPrimAtPath("/Environment/defaultLight").GetAttribute("visibility").Set("invisible")
def _compute_image_observations(self):
# generate ground truth keypoints for in-hand cube
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment