- 03 Aug, 2024 1 commit
-
-
Kelly Guo authored
# Description - Adds `min_step_count_between_reset` for Event terms to specify minimum randomization frequency for reset randomizations - Switch to numpy for material bucketing logic - Updates SH Config with DR ## Type of change - Bug fix (non-breaking change which fixes an issue) ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] 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 - [x] I have run all the tests with `./isaaclab.sh --test` and they pass - [x] 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
-
- 02 Aug, 2024 13 commits
-
-
James Smith authored
# Description NOTE: This is a redo of https://github.com/isaac-orbit/IsaacLab/pull/524, only rebased onto new main and with changes to work with Isaac Lab. Copied from other PR: Modifies container.sh and x11.yaml to automatically check if a tmp.***.xauth file has a stale MIT-MAGIC-COOKIE-1, and refreshes it if so. In the instance where an xsession ends after a `tmp.***.xauth` file has been created, but the system is not rebooted (thus deleting `tmp.***.xauth`) then attempting to use the container causes errors. This is a feature to correct for this upon `container.sh enter` by: 1. Mounting an entire `/tmp` subdirectory so that we can swap files 2. Checking for stale cookies by comparing against the current user's cookie 3. If stale, replacing the old `tmp.***.xauth` with a new `tmp.***.xauth` of the same name but a new cookie, in order to preserve functionality of envars. ## Type of change <!-- As you go through the list, delete the ones that are not applicable. --> - New feature (non-breaking change which adds functionality) ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./orbit.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 run all the tests with `./orbit.sh --test` and they pass - [ ] 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 --------- Signed-off-by:
James Smith <142246516+jsmith-bdai@users.noreply.github.com>
Co-authored-by:
Hunter Hansen <50837800+hhansen-bdai@users.noreply.github.com> -
Mayank Mittal authored
# Description Since we override a lot of the functions from RigidObject inside the Articulation class, we don't need to rely on inheritance anymore. Duplicacy in the code makes it easier to understand the two classes' functionalities without severely added overhead from the maintenance side. Moreover, conceptually, it can be motivated that the two are independent concepts. This MR decouples the rigid object and articulation concepts in the framework. ## Type of change - Breaking change (fix or feature that would cause existing functionality to not work as expected) - This change requires a documentation update ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] 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 - [x] 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 --------- Co-authored-by:
David Hoeller <dhoeller@nvidia.com> -
Kelly Guo authored
# Description - Removes unneeded extensions from headless app file - Limits CPU threads when running multi-GPU training to minimize thread context switching - Apply multi GPU renderer setting to avoid unnecessary GPU context initialization - Decreases 8k SH startup time on 8 GPUs from > 5 min to 1 min - Adds benchmarking scripts ## Type of change <!-- As you go through the list, delete the ones that are not applicable. --> - Bug fix (non-breaking change which fixes an issue) ## 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 - [x] I have updated the changelog and the corresponding version in the extension's `config/extension.toml` file - [ ] I have added my name to the `CONTRIBUTORS.md` or my name already exists there <!-- As you go through the checklist above, you can mark something as done by putting an x character in it For example, - [x] I have done this task - [ ] I have not done this task --> --------- Co-authored-by:
Alexander <143108850+nv-apoddubny@users.noreply.github.com>
Co-authored-by:
David Hoeller <dhoeller@nvidia.com> -
James Smith authored
# Description Add a cli argument `--extension` to run only unit tests for a selected extension. As an example: ```bash isaaclab -t --extension omni.isaac.lab_assets # Only runs tests under omni.isaac.lab_assets ``` Fixes #752 ## 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` - [x] 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
-
Mayank Mittal authored
# Description Earlier the README had hard-coded values for "passing" of pre-commit and docs. This changes it to use the GitHub actions instead. ## Type of change - This change requires a documentation update ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] 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
-
Pascal Roth authored
# Description Adds a parameter `border_height` to `TerrainGeneratorCfg` to be able to control the height of the generator border instead of having a hard-coded value of 1.0m. ## 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 - [x] 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
-
Mayank Mittal authored
# Description There was a slight inconsistency-- we called `unitree_a1`, `unitree_go1`, and at the same time `h1` and `g1`. This MR fixes this inconsistency and adds some more docs. ## Type of change - This change requires a documentation update ## 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 - [x] 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
-
Mayank Mittal authored
# Description The caching of terrains with the terrain generator did not work as expected even when the curriculum was enabled (which should have yielded the same terrain every time). On deeper investigation, it appears that the terrain generator samples a range when using the curriculum to avoid having the same sub-terrain in columns of the same terrain type. Thus, the terrain `difficulty` was stochastic between runs, which affected the caching of the terrain. This MR fixes the following: - Adds documentation of the above behavior - Modifies the generator to use `np.random.Generator` (RNG) instead of setting the seed globally - Adds a warning if the user wants to cache the terrain and the seed is not set - Adds tests to check caching works for the terrain generator with and without curriculum Note: Right now, complete determinism (i.e., the same terrain is generated) is only possible when seed is set and caching is enabled. If caching is disabled, it is possible that the terrain may have small differences. To fix this, the RNG needs to be propagated to all the generation functions as well. I leave that as a future TODO. ## Type of change - Bug fix (non-breaking change which fixes an issue) - This change requires a documentation update ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] I have made corresponding changes to the documentation - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective or that my feature works - [x] 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
-
Mayank Mittal authored
# Description This MR adds docstrings in articulation and rigid object data to clarify the exact frames they are reported in. This was previously causing confusion as PhysX reports the transforms in actor frame and velocities in CoM frame. Right now, there is no mechanism to get all this data in the same frame, so the best we can do is document behavior. ## Type of change - This change requires a documentation update ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] 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
-
Mayank Mittal authored
# Description This MR renames the action term names inside the manager-based lift-manipulation task. Earlier, they were called ``body_joint_pos`` and ``gripper_joint_pos``. This made it confusing since they were also being set to IK instead of joint position action terms. Now, they are called ``arm_action`` and ``gripper_action``. This makes it consistent with other manipulation tasks. ## Type of change - Breaking change (fix or feature that would cause existing functionality to not work as expected) - This change requires a documentation update ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] 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 - [x] 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
-
Masoud Moghani authored
# Description This MR removes the additional translation and orientation applied when creating the mesh prim under the parent Xform prim. ## Type of change - Bug fix (non-breaking change which fixes an issue) ## 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 - [x] 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
-
Mayank Mittal authored
# Description Previously, we used finite differencing to compute rigid body accelerations. Since Isaac Sim 4.0, we can obtain the accelerations directly from PhysX. This MR removes the need for finite differencing. ## Type of change - New feature (non-breaking change which adds functionality) - This change requires a documentation update ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] I have made corresponding changes to the documentation - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective or that my feature works - [x] 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
-
Mayank Mittal authored
# Description The previous implementation of `wrap_to_pi` was rather incorrect since it would map -PI to PI but -3PI to -PI. Following the general convention of this function (based on MATLAB), all odd positive multiples of PI should map to PI, and all negative multiples should map to -PI. This MR fixes the function and also adds a unit test for it. Fixes #770 ## Type of change - Bug fix (non-breaking change which fixes an issue) - Breaking change (fix or feature that would cause existing functionality to not work as expected) ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] I have made corresponding changes to the documentation - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective or that my feature works - [x] 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
-
- 30 Jul, 2024 1 commit
-
-
Mayank Mittal authored
# Description There were still a few changes not propagated with the drop of 2023.1.1. This MR fixes those pieces: - updating the version number in the docs to 4.1 - updating the nucleus asset server path to 4.1 - removing the physics flushing inside the interactive scene (as it was needed in 2023.1.1 only) ## Type of change - Bug fix (non-breaking change which fixes an issue) ## 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
-
- 27 Jul, 2024 1 commit
-
-
David Hoeller authored
# Description Updates code to Isaac Sim 4.1.0 release. ## 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
-
- 26 Jul, 2024 1 commit
-
-
Johnson Sun authored
# Description Clarify X11 forwarding configs in docs and warning messages. ## Type of change - Bug fix (non-breaking change which fixes an issue) ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] 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
-
- 23 Jul, 2024 4 commits
-
-
Masoud Moghani authored
# Description Fixes action term in the IK reach environment configurations. ## Type of change - Bug fix (non-breaking change which fixes an issue) ## 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 - [ ] I have added my name to the `CONTRIBUTORS.md` or my name already exists there
-
David Hoeller authored
# Description The render interval for reach environments was not equal to the decimation, resulting in unnecessary rendering steps. ## Type of change - Bug fix (non-breaking change which fixes an issue) ## 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
-
Luis Carranza authored
# Description Fixes #698 The sanity check compares the total actuator joints (total_act_joints) with the difference between the number of joints minus the number of fixed tendons (self.num_joints - self.num_fixed_tendons), but the warning message displays a comparison between total_act_joints and self.num_joints. This is misleading on complex robots that includes fixed tendons such as Franka hand. ## Type of change - Bug fix (non-breaking change which fixes an issue)
-
Vladimir Fokow authored
# Description Fixes inaccuracy in migration docs. Now the docs correspond to the actual code. Fixes #706 ## Type of change - This change requires a documentation update ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] I have made corresponding changes to the documentation - [ ] 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
-
- 17 Jul, 2024 3 commits
-
-
Hunter Hansen authored
# Description Changes made in [PR #628](https://github.com/isaac-sim/IsaacLab/commit/455a174849736ce0038b31fe7b17479a16e385e5) caused using the VSCode Debugger from `isaac-lab-base/-ros2` to no longer function because `python.sh` was not being called. This is because even though `{workspace}/_isaac_sim/python.sh` is initially set as the default, `setup_vscode.py` replaces it with the python binary that `python.sh` invokes, but without using `python.sh` certain envar modifications don't happen such that e.g. `PYTHONPATH` is broken and imports don't work. This change checks if the calling executable matches the exact path we expect with the isaac-lab containers, and then keeps it as the default if it does. ## Type of change - Bug fix (non-breaking change which fixes an issue) ## 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
-
robotsfan authored
# Description Fixes docstring in reward functions and code block in documentation ## Type of change - Bug fix ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] 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
-
Sudhir Pratap Yadav authored
# Description - Fixes https://github.com/isaac-sim/IsaacLab/issues/541 - **Bug description:** UR10 reach can be trained with RSL_RL but not with RL_GAMES and SKRL. - **Why this problem occurs:** The actual problem is there is no `__init__.py` file in the `agents` folder inside ur_10. Therefore when `mod_path = os.path.dirname(importlib.import_module(mod_name).__file__)` line is executed it gives error as `importlib.import_module(mod_name).__file__` is not able to find the module `omni.isaac.lab_tasks.manager_based.manipulation.reach.config.ur_10.agents`. ## Fixes - `__init__.py` file is added inside the ur_10.agents folder. ## Type of change - Bug fix (non-breaking change which fixes an issue) ## 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 - [ ] I have added my name to the `CONTRIBUTORS.md` or my name already exists there
-
- 13 Jul, 2024 3 commits
-
-
Mayank Mittal authored
# Description Earlier, the "startup" events were only triggered when used inside an RL environment. This MR makes sure they are also called inside the simple environment version as well. Fixes #664 ## Type of change - Bug fix (non-breaking change which fixes an issue) ## 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 - [x] 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
-
Mayank Mittal authored
# Description This MR adds schemas and spawners to create deformable bodies based on primitive shapes. It uses the latest PhysX 5.4 support for FEM simulation of deformable bodies. The MR adds the required demo and docs changes. ## Type of change - New feature (non-breaking change which adds functionality) - This change requires a documentation update ## Screenshots https://github.com/isaac-sim/IsaacLab/assets/12863862/9c239d6d-098d-4c70-b6fd-0a73c74c80c4 ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] 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
-
David Hoeller authored
# Description Adds RL configs to the Franka cabinet play environment ## Type of change - Bug fix (non-breaking change which fixes an issue) ## 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
-
- 10 Jul, 2024 2 commits
-
-
James Smith authored
# Description This PR: * enables per test timeout setting. * reduces default timeout to 2 mins (120 secs) * sets `test_environments.py` to have a timeout of 20 mins (1200 secs) * mounts `tools` dir into docker container Fixes #548 <!-- As a practice, it is recommended to open an issue to have discussions on the proposed pull request. This makes it easier for the community to keep track of what is being developed or added, and if a given feature is demanded by more than one party. --> ## 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 - [x] I have run all the tests with `./isaaclab.sh --test` and they pass - [ ] 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
-
James Smith authored
Fixes bug introduced in https://github.com/isaac-sim/IsaacLab/pull/621 The error was using `os.path.abspath()` instead of `os.path.isabs()` to check if a path exists. This would always return a value (as it actually converts to an absolute path) so the if branch was never entered for relative paths. Fixes #556 ## Type of change <!-- As you go through the list, delete the ones that are not applicable. --> - Bug fix (non-breaking change which fixes an issue) ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] 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
-
- 06 Jul, 2024 6 commits
-
-
David Hoeller authored
# Description Fixes Isaac Lab conda installation ## Type of change - Bug fix (non-breaking change which fixes an issue) ## 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
-
Mayank Mittal authored
# Description Realized that #631 did not deal properly with the case when not in a conda or docker. This MR re-writes the logic to hopefully make the operation safe. ## Type of change - Bug fix (non-breaking change which fixes an issue) ## 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 - [ ] 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
-
robotsfan authored
# Description There were minor quote issues in the docker container instructions. This MR fixes those. ## Type of change - This change requires a documentation update ## Checklist - [ ] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] I have made corresponding changes to the documentation - [ ] 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
-
Kelly Guo authored
# Description Previously, we always assumed heterogeneous environment setup, which performed cloning on a per-actor basis during spawning of actors. In some direct workflow environments, a redundant cloning call was made at the end of environment setup to perform cloning on a global scope. With this change, we determine whether to perform cloning on a per-actor or global scope based on the `replicate_physics` parameter in `InteractiveSceneCfg`. When `replicate_physics=True`, homogeneous environment is assumed and cloning will only happen on a global scope. This reduces the time required for cloning for homogeneous setups. For heterogeneous environments, set `replicate_physics=False` and cloning will happen per-actor. ## Type of change - Bug fix (non-breaking change which fixes an issue) - New feature (non-breaking change which adds functionality) - This change requires a documentation update ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] 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 - [x] 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
-
Mayank Mittal authored
# Description Earlier the script hard-coded with path to Isaac Sim installation as the sym-linked directory "_isaac_sim". However, when doing PIP installation, this workflow doesn't hold. The MR modifies the scripts `isaaclab.sh` and `isaaclab.bat` to now check for PIP package installation and get paths from there if they exist. Fixes #516, #629 ## Type of change - Bug fix (non-breaking change which fixes an issue) ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] I have made corresponding changes to the documentation - [ ] 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 --------- Signed-off-by:
Mayank Mittal <12863862+Mayankm96@users.noreply.github.com>
Co-authored-by:
Kelly Guo <kellyg@nvidia.com> -
David Hoeller authored
# Description Since the LiDAR configuration was added to the assets extension, the `test_valid_configs` test is failing. This MR removes sensors from configuration testing. The current set-up is not suitable for sensors, which require additional set-up (like creating a prim first or adding a mesh for the LiDAR). ## Type of change - Bug fix (non-breaking change which fixes an issue) ## 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 - [x] 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
-
- 05 Jul, 2024 3 commits
-
-
Pascal Roth authored
# Description Add a lidar pattern for the `RayCaster` sensor. The pattern is determined by number of channels, horizontal and vertical field of view and corresponding horizontal resolution. An example config for a Velodyne VLP 16 is provided. ## Type of change - New feature (non-breaking change which adds functionality) ## Screenshots  ## 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 - [x] 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
-
Mayank Mittal authored
# Description The deprecation notice has been out for a while. The MR removes the body PhysX view from the rigid object and articulation classes. This is no longer needed as their respective root views expose all the data needed for them. This is a breaking change, and we lose compatibility with Isaac Sim 2023.1.1. Fixes #237 ## Type of change - Bug fix (non-breaking change which fixes an issue) - Breaking change (fix or feature that would cause existing functionality to not work as expected) - This change requires a documentation update ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] 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 - [x] 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
-
Mayank Mittal authored
# Description This MR mainly fixes the documentation to make instructions clearer. The script was unclear about where the workspace path needs to be and how it can be resolved. The MR makes sure these cases are dealt and reported correctly. ## Type of change - This change requires a documentation update ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] 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
-
- 04 Jul, 2024 2 commits
-
-
Mayank Mittal authored
# Description Ever since we upgraded the torch version from 2.0.1 (in Isaac Sim 2023.1.1) to 2.2 (in Isaac Sim 4.0), we have seen some of the tests (such as `test_articulation.py`) fail due to improper deinitialization of the created class. This MR fixes this issue by creating a dummy tensor inside the `SimulationContext` in Isaac Lab. While this is a hack, it is effective and helps alleviate the problem. It is hard to figure out the root cause without really understanding what changed on the torch side. Fixes #639 ## Type of change - Bug fix (non-breaking change which fixes an issue) - This change requires a documentation update ## 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
-
Shafeef Omar authored
# Description This pull request adds support for running IsaacLab on clusters that use PBS job schedulers (e.g. Franklin@IIT). Currently, it only supports SLURM. The job submission scripts have been modified to choose between SLURM or PBS job schedulers. The user can opt for the required job scheduler from `docker/cluster/.env.base` under cluster specific settings. Tested successfully on Franklin@IIT HPC. Fixes #599 ## Type of change - New feature (non-breaking change which adds functionality) - This change requires a documentation update ## Checklist - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [x] 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 run all the tests with `./isaaclab.sh --test` and they pass - [ ] 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
-