Fixes TiledCamera data types and rlgames training on CPU#3808
Merged
kellyguo11 merged 5 commits intoOct 27, 2025
Conversation
Contributor
There was a problem hiding this comment.
Greptile Overview
Greptile Summary
This PR fixes two critical bugs affecting CPU-based simulations: (1) TiledCamera was incorrectly converting all numpy arrays to uint8 warp arrays, causing data corruption for depth (float32) and segmentation (uint32) data, and (2) RL-Games training scripts weren't respecting the --device command-line argument. The TiledCamera fix removes the hardcoded dtype parameter in tiled_camera.py, allowing warp to infer the correct type from the numpy array. The RL-Games fix propagates the device setting from CLI args to the agent configuration in three scripts: train.py, play.py, and benchmark_rlgames.py, aligning with the existing RSL RL implementation pattern. The changes include comprehensive test coverage with device parametrization and proper version/changelog updates.
Potential Issues:
-
In
train.py, there's a subtle conflict: when both--device cpuand--distributedflags are specified, the distributed training block (lines 119-125) unconditionally overrides the device to CUDA with local rank. This means--device cpu --distributedwould be silently ignored and forced to use CUDA. Consider adding validation to prevent conflicting flags or documenting that distributed training requires CUDA. -
The test parametrization change restricts three tests (
test_throughput,test_frame_offset_small_resolution,test_frame_offset_large_resolution) to CUDA-only without clear documentation in comments explaining why. This could lead to confusion about whether these features are unsupported on CPU or just untested.
Confidence: 4/5 - The core fixes are sound and well-tested, but the distributed training device override could cause confusion for users expecting CPU training with distributed mode.
7 files reviewed, 1 comment
Comment on lines
+99
to
+101
| if args_cli.device is not None: | ||
| agent_cfg["params"]["config"]["device"] = args_cli.device | ||
| agent_cfg["params"]["config"]["device_name"] = args_cli.device |
Contributor
There was a problem hiding this comment.
logic: device setting is overridden again on lines 121-122 when distributed training is enabled, potentially discarding user-specified device. Should the distributed training device override apply only when args_cli.device is None?
Mayankm96
approved these changes
Oct 24, 2025
Mayankm96
left a comment
Contributor
There was a problem hiding this comment.
Thanks a lot for the fix! :)
ooctipus
approved these changes
Oct 24, 2025
Contributor
There was a problem hiding this comment.
Greptile Overview
Greptile Summary
This review covers only the changes made since the last review, not the entire PR. The previous review noted a device override issue in distributed training scenarios. The latest changes focus on adding comprehensive test coverage and validation logic. Specifically, tests for TiledCamera have been parametrized to run on both CUDA and CPU devices to validate the data type conversion fix. Additionally, validation checks have been added across all RL training scripts (rl_games, rsl_rl, skrl) and benchmarks to prevent the invalid combination of CPU device with distributed training, which would fail since distributed training requires CUDA. These validation checks ensure users receive clear error messages when attempting unsupported configurations, rather than encountering cryptic runtime failures.
Important Files Changed
| Filename | Score | Overview |
|---|---|---|
| source/isaaclab/isaaclab/sensors/camera/tiled_camera.py | 5/5 | Fixed critical data type bug by removing hardcoded uint8 casting, allowing warp to infer correct dtype from numpy arrays for depth and segmentation data |
| source/isaaclab/test/sensors/test_tiled_camera.py | 4/5 | Added device parametrization to test functions enabling CPU and CUDA testing, validating the TiledCamera dtype fix |
| scripts/reinforcement_learning/rl_games/train.py | 4/5 | Added device propagation to agent config and validation to prevent distributed training on CPU |
| scripts/reinforcement_learning/rl_games/play.py | 5/5 | Propagates command-line device setting to agent configuration for device consistency |
| scripts/benchmarks/benchmark_rlgames.py | 4/5 | Added device propagation and validation for distributed training compatibility |
| scripts/reinforcement_learning/rsl_rl/train.py | 4.5/5 | Added validation preventing CPU device usage with distributed training |
| scripts/reinforcement_learning/skrl/train.py | 5/5 | Added device validation check positioned correctly before distributed override logic |
| scripts/benchmarks/benchmark_rsl_rl.py | 3/5 | Added validation but may have logic issue checking args_cli.device instead of env_cfg.sim.device after override |
| scripts/benchmarks/benchmark_non_rl.py | 5/5 | Added validation check for CPU+distributed with clear error message |
| source/isaaclab/config/extension.toml | 5/5 | Version bumped to 0.47.2 following semantic versioning for bug fix |
| source/isaaclab/docs/CHANGELOG.rst | 5/5 | Documented data type conversion fix for TiledCamera in version 0.47.2 |
Confidence score: 4/5
- This PR is generally safe to merge but requires attention to a few validation logic concerns
- Score reflects well-tested core fix for TiledCamera dtype bug, but deducted one point due to: (1) potential validation logic issue in benchmark_rsl_rl.py checking args_cli.device instead of the post-override env_cfg.sim.device, and (2) the previously noted device override issue in distributed training scenarios where user-specified CPU device gets overridden
- Pay close attention to scripts/benchmarks/benchmark_rsl_rl.py validation logic and all scripts with distributed training device override logic (train.py files)
11 files reviewed, 5 comments
Comment on lines
+139
to
+141
| if args_cli.device is not None: | ||
| agent_cfg["params"]["config"]["device"] = args_cli.device | ||
| agent_cfg["params"]["config"]["device_name"] = args_cli.device |
Contributor
There was a problem hiding this comment.
style: device setting is overridden again on lines 152 and 169-170 when distributed training is enabled. Consider consolidating device logic to avoid redundant assignments
Comment on lines
+144
to
+148
| if args_cli.distributed and args_cli.device is not None and "cpu" in args_cli.device: | ||
| raise ValueError( | ||
| "Distributed training is not supported when using CPU device. " | ||
| "Please use GPU device (e.g., --device cuda) for distributed training." | ||
| ) |
Contributor
There was a problem hiding this comment.
logic: check occurs after device override on line 142, so args_cli.device could still be None here. The validation should check env_cfg.sim.device instead after the override is applied.
| @@ -118,6 +118,12 @@ def main(env_cfg: ManagerBasedRLEnvCfg | DirectRLEnvCfg | DirectMARLEnvCfg, agen | |||
| # note: certain randomizations occur in the environment initialization so we set the seed here | |||
| env_cfg.seed = agent_cfg.seed | |||
| env_cfg.sim.device = args_cli.device if args_cli.device is not None else env_cfg.sim.device | |||
Contributor
There was a problem hiding this comment.
style: device assignment occurs here before distributed training check on line 122, but gets overridden on line 130when distributed is enabled. Consider reordering to avoid unnecessary assignment.
|
|
||
| @pytest.fixture(scope="function") | ||
| def setup_camera() -> tuple[sim_utils.SimulationContext, TiledCameraCfg, float]: | ||
| def setup_camera(device) -> tuple[sim_utils.SimulationContext, TiledCameraCfg, float]: |
Contributor
There was a problem hiding this comment.
style: fixture parameter should have type annotation for consistency with pytest conventions
Comment on lines
+75
to
+77
| @pytest.mark.parametrize("device", ["cuda:0", "cpu"]) | ||
| @pytest.mark.isaacsim_ci | ||
| def test_single_camera_init(setup_camera): | ||
| def test_single_camera_init(setup_camera, device): |
Contributor
There was a problem hiding this comment.
logic: the device parameter is shadowing the fixture parameter and is redundant - pytest automatically passes the parametrized value to the fixture. Should the device parameter be removed from the test function signatures since it's already injected by parametrize into the setup_camera fixture?
kellyguo11
added a commit
that referenced
this pull request
Oct 27, 2025
We were incorrectly converting all numpy array data in the TiledCamera class into uint8 type warp arrays when simulation device is set to CPU. Some annotations like depth are float32 while segmentation data is uint32. The correct behavior should convert to warp arrays depending on the input data type of the numpy array. Additionally, rlgames configs were set to cuda device by default but were not being overridden when users specify the simulation device to CPU through cmdline. We should propagate the device setting to the rlgames configs so that we can run training on the same device, similar to how RSL RL is set up. Fixes #3526 - Bug fix (non-breaking change which fixes an issue) - [x] I have read and understood the [contribution guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html) - [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 <!-- 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 -->
jnskkmhr
added a commit
to jnskkmhr/IsaacLab
that referenced
this pull request
Oct 29, 2025
* Provides PBT training cfg example for Isaac-Dexsuite-Kuka-Allegro-Lift-v0 env for rl_games (#3553)
# Description
This PR provides a PBT builtin training example for
Isaac-Dexsuite-Kuka-Allegro-Lift-v0 environment.
Though we had introduction and explanation for how to run PBT, We didn't
have an builtin example.
This will make using PBT easier for user.
Fixes # (issue)
<!-- 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)
## Screenshots
Please attach before and after screenshots of the change if applicable.
<!--
Example:
| Before | After |
| ------ | ----- |
| _gif/png before_ | _gif/png after_ |
To upload images to a PR -- simply drag and drop an image while in edit
mode and it should upload the image directly. You can then paste that
source into the above before/after sections.
-->
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
<!--
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
-->
* [Newton] Adds policy transfer script for sim2sim transfer from Newton to physX (#3565)
# Description
This PR adds a play script to physX-based IsaacLab to make it possible
to play a Newton-based trained policy. Tested environments are
H1/G1/Anymal-D but other exisiting Newton environment should transfer as
well.
<!--
Thank you for your interest in sending a pull request. Please make sure
to check the contribution guidelines.
Link:
https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html
💡 Please try to keep PRs small and focused. Large PRs are harder to
review and merge.
-->
Please include a summary of the change and which issue is fixed. Please
also include relevant motivation and context.
List any dependencies that are required for this change.
Fixes # (issue)
<!-- 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
<!-- As you go through the list, delete the ones that are not
applicable. -->
- Bug fix (non-breaking change which fixes an issue)
- New feature (non-breaking change which adds functionality)
- Breaking change (existing functionality will not work without user
modification)
- Documentation update
## Screenshots
Please attach before and after screenshots of the change if applicable.
<!--
Example:
| Before | After |
| ------ | ----- |
| _gif/png before_ | _gif/png after_ |
To upload images to a PR -- simply drag and drop an image while in edit
mode and it should upload the image directly. You can then paste that
source into the above before/after sections.
-->
## Checklist
- [ ] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [ ] 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
- [ ] 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
-->
---------
Signed-off-by: Milad Rakhsha <mrakhsha@nvidia.com>
* Randomizes viscous and dynamic joint friction based on IsaacSim 5.0 (#3318)
# Description
<!--
Thank you for your interest in sending a pull request. Please make sure
to check the contribution guidelines.
Link:
https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html
-->
This PR fixes https://github.com/isaac-sim/IsaacLab/issues/3266, adding
the possibility to randomize the friction coefficient when isaacsim is
higher than 5.0.0
<!-- 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
<!-- As you go through the list, delete the ones that are not
applicable. -->
- New feature (non-breaking change which adds functionality)
## Screenshots
Not applicable
<!--
Example:
| Before | After |
| ------ | ----- |
| _gif/png before_ | _gif/png after_ |
To upload images to a PR -- simply drag and drop an image while in edit
mode and it should upload the image directly. You can then paste that
source into the above before/after sections.
-->
## 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
<!--
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
-->
---------
Signed-off-by: Giulio Romualdi <giulio.romualdi@gmail.com>
Signed-off-by: Mayank Mittal <12863862+Mayankm96@users.noreply.github.com>
Co-authored-by: James Tigue <166445701+jtigue-bdai@users.noreply.github.com>
Co-authored-by: Mayank Mittal <12863862+Mayankm96@users.noreply.github.com>
* Fixes broken link to conda in installation doc (#3601)
Fixes broken link to conda in installation doc
* Adds link to IsaacLabEvalTasks repo from mimic section in doc (#3621)
# Description
<!--
Thank you for your interest in sending a pull request. Please make sure
to check the contribution guidelines.
Link:
https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html
💡 Please try to keep PRs small and focused. Large PRs are harder to
review and merge.
-->
Isaac Lab Mimic section is disjoint from [IsaacLabEvalTask
repo](https://github.com/isaac-sim/IsaacLabEvalTasks/tree/main) which
uses Mimic to generate Nut pouring task and Pipe sorting task for GR00T
post-training and closedloop evaluation. Added a pointer in the doc.
<!-- 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
Documentation update
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
<!--
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
-->
* Updated docker image builds with new requirements (#3613)
# Description
Enabling multi-arch build with Isaac SIM 5.1 images
* Forces CRLF for .bat files to prevent script execution errors on Windows (#3624)
# Description
Fix windows script execution error as described in [Discussions
3260](https://github.com/isaac-sim/IsaacLab/discussions/3260), by
forcing to use crlf as eol in `*.bat` file
## Type of change
- Bug fix (non-breaking change which fixes an issue)
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
* Fixes minor typos in the documentation (#3584)
# Description
Fixes minor typos in the documentation.
## Type of change
- Bug fix (non-breaking change which fixes an issue)
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
- [ ] I have added my name to the `CONTRIBUTORS.md` or my name already
exists there
* Fixes SB3's template ppo cfg up to date with security-safe syntax for training specification (#3688)
# Description
This PR fixes the bug where if template is generated using SB3, the code
does not run because it couldn't parse from string
```
policy_kwargs: "dict(
activation_fn=nn.ELU,
net_arch=[32, 32],
squash_output=False,
)"
```
We have disabled the string parsing, as it is not safe(aka arbitrary
code could be parsed)
this PR makes sure the sb3's template also adopt the new secure syntax
```
policy_kwargs:
activation_fn: nn.ELU
net_arch: [32, 32]
squash_output: False
```
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
<!--
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
-->
* Uses the configuration to obtain the simulation device (#3636)
# Description
This MR fixes the slow-down observed in recent IsaacLab updates.
Previously, the simulation device was read through the configuration;
later, this was changed to read the device through the simulation
manager.
On profiling, I observed that the simulation manager function took 0.01
s per call. This is quite a bit of overhead, considering that
`env.device` refers to `sim.device` and gets called at multiple
locations in the environment.
This MR reverts back to the previous solution for obtaining the device.
Fixes #3554
## Type of change
- Bug fix (non-breaking change which fixes an issue)
## Screenshots
```
./isaaclab.sh -p scripts/benchmarks/benchmark_non_rl.py --task Isaac-Velocity-Flat-Anymal-C-v0 --headless --seed 0 --num_frames 2000
```
The numbers reported here are the average FPS on PC with RTX A6000 GPU
and Intel i9-9820X:
* **Before**: 94784.43553363248
* **Overriding `sim.device`**: 100484.21244511564
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
* Adds msgpack to license exception (#3687)
# Description
msgpack is required by ray when installing rl_games. it has an apache
2.0 license, so we are adding it to the exceptions list since the
license shows up as UNKNOWN by the license checker.
## Type of change
<!-- As you go through the list, delete the ones that are not
applicable. -->
- Documentation update
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
- [ ] 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
-->
* Fixes skrl train/play script configurations when using the `--agent` argument and rename agent configuration variable (#3643)
# Description
This PR address the following points:
* Fix skrl train/play script configuration when using the `--agent`
argument
Example:
```bash
python scripts/reinforcement_learning/skrl/train.py --task
Isaac-Cart-Double-Pendulum-Direct-v0 --headless --agent
skrl_mappo_cfg_entry_point
```
Error:
```
[INFO]: Parsing configuration from:
isaaclab_tasks.direct.cart_double_pendulum.cart_double_pendulum_env:CartDoublePendulumEnvCfg
[INFO]: Parsing configuration from:
/home/toni/Documents/RL/toni_IsaacLab/source/isaaclab_tasks/isaaclab_tasks/direct/cart_double_pendulum/agents/skrl_mappo_cfg.yaml
[INFO] Logging experiment in directory:
/home/toni/Documents/RL/toni_IsaacLab/logs/skrl/cart_double_pendulum_direct
Error executing job with overrides: []
Traceback (most recent call last):
File
"/home/toni/Documents/RL/toni_IsaacLab/source/isaaclab_tasks/isaaclab_tasks/utils/hydra.py",
line 101, in hydra_main
func(env_cfg, agent_cfg, *args, **kwargs)
File
"/home/toni/Documents/RL/toni_IsaacLab/scripts/reinforcement_learning/skrl/train.py",
line 156, in main
log_dir = datetime.now().strftime("%Y-%m-%d_%H-%M-%S") +
f"_{algorithm}_{args_cli.ml_framework}"
^^^^^^^^^
NameError: name 'algorithm' is not defined
```
* Replace `STATES` by `OBSERVATIONS` when defining skrl's agent
configuration model inputs to ensure a smooth and error-free transition
when the new mayor version of **skrl** gets released. In such mayor
version `OBSERVATIONS` and `STATES` have different value/usage.
## 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)
* Updates SkillGen documentation for data gen command and success rates (#3702)
# SkillGen documentation: data gen command cleanup and success-rate
guidance
## Description
This PR updates the SkillGen documentation in
`docs/source/overview/imitation-learning/skillgen.rst`:
- Removes a redundant `--headless` flag from a data generation command
example.
- Adds a note with success-rate guidelines and training recommendations
for cube stacking and bin cube stacking.
- Clarifies minor text details, including correcting the planning phase
order to “Retreat → Contact → Approach” for consistency.
Motivation: Improve clarity, set realistic expectations on data
generation and downstream policy performance, and align docs with actual
planner behavior.
Dependencies: None
## Type of change
- Documentation update
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
* Configures mesh collision schemas in `convert_mesh.py` (#3558)
# Description
The collision approximation configuration changed in main branch, but
the code in tools/convert_mesh.py does not sync.
Fixes #3557
## Type of change
- Bug fix (non-breaking change which fixes an issue)
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
---------
Signed-off-by: zehao-wang <59912787+zehao-wang@users.noreply.github.com>
* Fixes warnings when running AutoMate env (#3660)
# Description
* Fixes the warning messages reported in the QA testing
* Remove redundant config argument 'sample_from'
* Change the default value of config argument 'num_log_traj'
## Type of change
- Bug fix (non-breaking change which fixes an issue)
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
---------
Co-authored-by: Kelly Guo <kellyg@nvidia.com>
* Exposes `physxscene:solveArticulationContactLast` flag through PhysxCfg (#3502)
# Description
This PR adds api to set physxscene:solveArticulationContactLast through
PhysxCfg,
this is only available in sim 5.1
Fixes # (issue)
## Type of change
<!-- As you go through the list, delete the ones that are not
applicable. -->
- New feature (non-breaking change which adds functionality)
## Screenshots
Please attach before and after screenshots of the change if applicable.
<!--
Example:
| Before | After |
| ------ | ----- |
| _gif/png before_ | _gif/png after_ |
To upload images to a PR -- simply drag and drop an image while in edit
mode and it should upload the image directly. You can then paste that
source into the above before/after sections.
-->
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
<!--
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
-->
---------
Signed-off-by: ooctipus <zhengyuz@nvidia.com>
Co-authored-by: Mayank Mittal <12863862+Mayankm96@users.noreply.github.com>
* Updates CODEOWNERS for Isaac Lab Mimic (#3714)
# Description
Update CODEOWNERS for Isaac Lab Mimic
## Type of change
- Documentation update
## Checklist
- [ ] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [ ] 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
- [ ] 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
-->
Signed-off-by: Yan Chang <yachang@nvidia.com>
* Update gymnasium dependency to version 1.2.1 (#3696)
# Description
This MR updates gymnasium version to prevent memory leak while video
recording.
Related MR: https://github.com/Farama-Foundation/Gymnasium/pull/1444
Fixes https://github.com/isaac-sim/IsaacLab/pull/3387
## Type of change
- Bug fix (non-breaking change which fixes an issue)
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
Signed-off-by: Mayank Mittal <12863862+Mayankm96@users.noreply.github.com>
Co-authored-by: ooctipus <zhengyuz@nvidia.com>
* Updates SB3 ppo cfg so it trains under reasonable amount of time (#3726)
# Description
This PR fixes the sb3_ppo_cfg for task Isaac-Ant-v0
the parameter before had 4096 num_envs + horizon 512 + batch size 128 +
n_epoch 20,
that means the training one cycle it needs to for loop (20 * 512 * 4096)
/ 128 = 327680 times!
which appears as if it is hanging forever
the new config matches more closely with that of rl_games.
I verified it will trains under 5 min
[Screencast from 2025-10-15
13-56-21.webm](https://github.com/user-attachments/assets/2bc7bcd8-0063-46b9-adb0-67a6aa686732)
## 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)
## Screenshots
Please attach before and after screenshots of the change if applicable.
<!--
Example:
| Before | After |
| ------ | ----- |
| _gif/png before_ | _gif/png after_ |
To upload images to a PR -- simply drag and drop an image while in edit
mode and it should upload the image directly. You can then paste that
source into the above before/after sections.
-->
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
<!--
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
-->
* Fixes the way seed was set in the benchmark_non_rl script (#3741)
# Description
When seed was added to the benchmark_non_rl.py script, it was mistakenly
trying to read from simulation config, which doesn't exist. We can set
seed directly from the cli arguments since it's ok to be None if it's
not specified.
## 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 read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
- [ ] 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
-->
* Removes pickle dependency for cfg load and dump (#3709)
# Description
We have been supporting both pickle and yaml storing for configuration.
However, pickle has some security vulnerabilities and we have been
preferring the use of yaml in most cases. Thus, we are removing the
pickle utilities for saving and loading configs.
For more info on pickle: https://docs.python.org/3/library/pickle.html
## Type of change
- Breaking change (existing functionality will not work without user
modification)
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
---------
Signed-off-by: Kelly Guo <kellyg@nvidia.com>
Co-authored-by: Mayank Mittal <12863862+Mayankm96@users.noreply.github.com>
* Adds functions to obtain prim pose and scale from USD Xformable (#3371)
# Description
This MR adds two functions to obtain the pose and scale of a prim
respectively.
This is needed for #3298.
## 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
- [ ] 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: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Kelly Guo <kellyg@nvidia.com>
* Sets reward computation in AutoMate env with CUDA or CPU (#3733)
# Description
If Nvidia driver 580 and cuda toolkit 13.0, we compute reward with CPU.
If Nvidia driver 570 and cuda toolkit 12.8, we compute reward with CUDA.
Fixes issue with hanging process with cuda 13.
## Type of change
- Bug fix (non-breaking change which fixes an issue)
- Documentation update
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
- [ ] I have added my name to the `CONTRIBUTORS.md` or my name already
exists there
---------
Signed-off-by: Kelly Guo <kellyg@nvidia.com>
Co-authored-by: Kelly Guo <kellyg@nvidia.com>
* Normalizes line endings for docs/make.bat (#3757)
# Description
When cloning the repo, make.bat caused line ending changes to be
triggered on Linux due to difference in Windows and Linux styles. This
change normalizes the script to avoid triggering git conversions when
cloning the repo.
## Type of change
- Bug fix (non-breaking change which fixes an issue)
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
* Adds data gen and policy learning times in SkillGen documentation (#3773)
## Description
This PR updates the SkillGen docs to include expected data generation
and policy training times for clarity.
Dependencies: None
## Type of change
- Documentation update
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
* Fixes typo in rl-games configuration for cartpole task (#3767)
# Description
Fixed a typo in the RL Games PPO configuration file for the Cartpole
feature-based environment. Changed value_bootstraop to value_bootstrap
on line 60 to match the correct parameter name used throughout the
codebase.
## Type of change
- Bug fix (non-breaking change which fixes an issue)
## Screenshots
Not applicable (text-only typo fix in YAML configuration file)
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
<!--
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
-->
Signed-off-by: G.G <148413288+tkgaolol@users.noreply.github.com>
* Updates cuRobo installation instructions and added VRAM baseline perf to SkillGen docs (#3796)
### Description
- Add a concise installation caveat for cuRobo when Omniverse Kit/Isaac
Sim environment scripts set `PYTHONPATH`/`PYTHONHOME`, with simple
mitigations.
- Clarify `TORCH_CUDA_ARCH_LIST` usage (match GPU compute capability;
add `+PTX` for forward compatibility).
- Consolidate and document VRAM usage baselines and GPU recommendations
for both Vanilla Cube Stacking and Adaptive Bin Cube Stacking (measured
over 10 demos on RTX 6000 Ada 48 GB).
- Minor wording fixes for consistency (e.g., “adaptive bin cube
stacking”).
- **Dependencies**: None
### Type of change
- Documentation update
### Checklist
- [x] I have read and understood the contribution guidelines
- [x] I have run the `pre-commit` checks 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
* Fixes cuda version as float for AutoMate to correctly convert patch versions (#3795)
# Description
To convert cuda version from a string to a float, I update the function
to handle cases with multiple points, e.g. string '12.8.9' will be
converted to float 12.89. Before, float('12.8.9') will return None for
failure conversion.
## Type of change
- Bug fix (non-breaking change which fixes an issue)
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
* Updates package licenses, CPU Governor setting in docs, and flaky tests (#3778)
# Description
There were some recent updates to a couple of our dependency packages
that have updated their licenses. Updating our license checker
exceptions to match with the new updated licenses for these packages.
Additionally, adds a note in the simulation performance documentation
for CPU governor setting to improve performance.
Also, updates a few unit tests to mark as flaky as we've shown in recent
CI runs.
## 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)
- Documentation update
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
- [ ] 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
-->
* Fixes TiledCamera data types and rlgames training on CPU (#3808)
# Description
We were incorrectly converting all numpy array data in the TiledCamera
class into uint8 type warp arrays when simulation device is set to CPU.
Some annotations like depth are float32 while segmentation data is
uint32. The correct behavior should convert to warp arrays depending on
the input data type of the numpy array.
Additionally, rlgames configs were set to cuda device by default but
were not being overridden when users specify the simulation device to
CPU through cmdline. We should propagate the device setting to the
rlgames configs so that we can run training on the same device, similar
to how RSL RL is set up.
Fixes #3526
## Type of change
- Bug fix (non-breaking change which fixes an issue)
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
<!--
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
-->
* Adds matplotlib-inline to license exceptions (#3853)
# Description
matplotlib-inline has BSD-3 license, so it's ok for us to include it. We
already have the license file specified for it.
## Type of change
- Documentation update
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
- [ ] 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
-->
* Merges release 2.3 changes into main with Isaac Sim 5.1 support (#3857)
# Description
Merging in updates for the Isaac Lab 2.3 release, moving to support for
Isaac Sim 5.1.
This change includes many features for teleoperation, disjoint
navigation, whole-body control for teleoperation, and IK updates from
@rwiltz, @michaellin6, @jaybdub, @huihuaNvidia2023, @hougantc-nvda,
@lotusl-code, @yami007007, @cathyliyuanchen, @tifchen-nvda.
Additionally, support for DGX Spark is added by @ooctipus and
@matthewtrepte.
For details of the changes and updates, refer to the release notes.
## Type of change
- New feature (non-breaking change which adds functionality)
- Breaking change (existing functionality will not work without user
modification)
- Documentation update
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
<!--
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
-->
---------
Signed-off-by: Harsh Patel <hapatel@theaiinstitute.com>
Signed-off-by: rebeccazhang0707 <168459200+rebeccazhang0707@users.noreply.github.com>
Signed-off-by: Kelly Guo <kellyg@nvidia.com>
Signed-off-by: yami007007 <weihuaz@nvidia.com>
Signed-off-by: Kelly Guo <kellyguo123@hotmail.com>
Signed-off-by: Louis LE LAY <le.lay.louis@gmail.com>
Signed-off-by: Mayank Mittal <12863862+Mayankm96@users.noreply.github.com>
Signed-off-by: Javier Felix-Rendon <javierfelixrendon@gmail.com>
Signed-off-by: Doug Fulop <dougfulop@gmail.com>
Signed-off-by: Milad Rakhsha <mrakhsha@nvidia.com>
Signed-off-by: Giulio Romualdi <giulio.romualdi@gmail.com>
Signed-off-by: zehao-wang <59912787+zehao-wang@users.noreply.github.com>
Signed-off-by: Michael Gussert <michael@gussert.com>
Signed-off-by: ooctipus <zhengyuz@nvidia.com>
Signed-off-by: shauryadNv <shauryad@nvidia.com>
Co-authored-by: Philipp Reist <66367163+preist-nvidia@users.noreply.github.com>
Co-authored-by: Harsh Patel <hapatel@theaiinstitute.com>
Co-authored-by: James Tigue <jtigue@theaiinstitute.com>
Co-authored-by: James Tigue <166445701+jtigue-bdai@users.noreply.github.com>
Co-authored-by: ooctipus <zhengyuz@nvidia.com>
Co-authored-by: rebeccazhang0707 <168459200+rebeccazhang0707@users.noreply.github.com>
Co-authored-by: michaellin6 <michalin@nvidia.com>
Co-authored-by: Huihua Zhao <huihuaz@nvidia.com>
Co-authored-by: Rafael Wiltz <rwiltz@nvidia.com>
Co-authored-by: Sergey Grizan <sgrizan@nvidia.com>
Co-authored-by: Alexander Poddubny <143108850+nv-apoddubny@users.noreply.github.com>
Co-authored-by: John <jaybdub@users.noreply.github.com>
Co-authored-by: yami007007 <weihuaz@nvidia.com>
Co-authored-by: Weihua Zhang <weihuaz@weihuaz-mlt.client.nvidia.com>
Co-authored-by: PeterL-NV <petliu@nvidia.com>
Co-authored-by: Mayank Mittal <12863862+Mayankm96@users.noreply.github.com>
Co-authored-by: hougantc-nvda <127865892+hougantc-nvda@users.noreply.github.com>
Co-authored-by: peterd-NV <peterd@nvidia.com>
Co-authored-by: njawale42 <njawale@nvidia.com>
Co-authored-by: Cathy Li <40371641+cathyliyuanchen@users.noreply.github.com>
Co-authored-by: Louis LE LAY <le.lay.louis@gmail.com>
Co-authored-by: Javier Felix-Rendon <javierfelixrendon@gmail.com>
Co-authored-by: Doug Fulop <dougfulop@gmail.com>
Co-authored-by: Robin Vishen <117207232+vi7n@users.noreply.github.com>
Co-authored-by: -T.K.- <t_k_233@outlook.com>
Co-authored-by: Mayank Mittal <mittalma@leggedrobotics.com>
Co-authored-by: Rebecca Zhang <rebeccaz@nvidia.com>
Co-authored-by: Lorenz Wellhausen <lorenwel@users.noreply.github.com>
Co-authored-by: Lorenz Wellhausen <lorenz.wellhausen@rivr.ai>
Co-authored-by: Michael Gussert <michael@gussert.com>
Co-authored-by: Antoine RICHARD <antoiner@nvidia.com>
Co-authored-by: tifchen-nvda <tifchen@nvidia.com>
Co-authored-by: Cathy Li <yuanchenl@yuanchenl-mlt.client.nvidia.com>
Co-authored-by: rwiltz <165190220+rwiltz@users.noreply.github.com>
Co-authored-by: Milad-Rakhsha-NV <167464435+Milad-Rakhsha-NV@users.noreply.github.com>
Co-authored-by: Milad-Rakhsha <miladrakhsha@gmail.com>
Co-authored-by: Giulio Romualdi <giulio.romualdi@gmail.com>
Co-authored-by: Xinjie Yao <xyao@nvidia.com>
Co-authored-by: shauryadNv <shauryad@nvidia.com>
Co-authored-by: Toni-SM <aserranomuno@nvidia.com>
Co-authored-by: zehao-wang <59912787+zehao-wang@users.noreply.github.com>
Co-authored-by: yijieg <yijieg@nvidia.com>
Co-authored-by: ndahile-nvidia <167997649+ndahile-nvidia@users.noreply.github.com>
Co-authored-by: matthewtrepte <mtrepte@nvidia.com>
Co-authored-by: yanziz-nvidia <yanziz@nvidia.com>
Co-authored-by: lotusl-code <lotusl@nvidia.com>
* Updates release notes and driver versions (#3868)
# Description
Documentation update for release notes for the 2.3 release and some
final updates on recommended driver versions.
## Type of change
- Documentation update
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
- [ ] 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 -->
Signed-off-by: Kelly Guo <kellyg@nvidia.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* Fixes broken link for Isaac-Tracking-LocoManip-Digit-v0 (#3883)
# Description
<!--
Thank you for your interest in sending a pull request. Please make sure
to check the contribution guidelines.
Link:
https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html
💡 Please try to keep PRs small and focused. Large PRs are harder to
review and merge.
-->
`Isaac-Tracking-LocoManip-Digit-v0` was moved to a different source code
path and docs were not updated accordingly. This change fixes the broken
URL.
## Type of change
<!-- As you go through the list, delete the ones that are not
applicable. -->
- Documentation update
## Checklist
- [x] I have read and understood the [contribution
guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html)
- [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
<!--
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
-->
---------
Signed-off-by: Milad Rakhsha <mrakhsha@nvidia.com>
Signed-off-by: Giulio Romualdi <giulio.romualdi@gmail.com>
Signed-off-by: Mayank Mittal <12863862+Mayankm96@users.noreply.github.com>
Signed-off-by: zehao-wang <59912787+zehao-wang@users.noreply.github.com>
Signed-off-by: ooctipus <zhengyuz@nvidia.com>
Signed-off-by: Yan Chang <yachang@nvidia.com>
Signed-off-by: Kelly Guo <kellyg@nvidia.com>
Signed-off-by: G.G <148413288+tkgaolol@users.noreply.github.com>
Signed-off-by: Harsh Patel <hapatel@theaiinstitute.com>
Signed-off-by: rebeccazhang0707 <168459200+rebeccazhang0707@users.noreply.github.com>
Signed-off-by: yami007007 <weihuaz@nvidia.com>
Signed-off-by: Kelly Guo <kellyguo123@hotmail.com>
Signed-off-by: Louis LE LAY <le.lay.louis@gmail.com>
Signed-off-by: Javier Felix-Rendon <javierfelixrendon@gmail.com>
Signed-off-by: Doug Fulop <dougfulop@gmail.com>
Signed-off-by: Michael Gussert <michael@gussert.com>
Signed-off-by: shauryadNv <shauryad@nvidia.com>
Co-authored-by: ooctipus <zhengyuz@nvidia.com>
Co-authored-by: Milad-Rakhsha-NV <167464435+Milad-Rakhsha-NV@users.noreply.github.com>
Co-authored-by: Giulio Romualdi <giulio.romualdi@gmail.com>
Co-authored-by: James Tigue <166445701+jtigue-bdai@users.noreply.github.com>
Co-authored-by: Mayank Mittal <12863862+Mayankm96@users.noreply.github.com>
Co-authored-by: Michael Gussert <michael@gussert.com>
Co-authored-by: Xinjie Yao <xyao@nvidia.com>
Co-authored-by: Alexander Poddubny <143108850+nv-apoddubny@users.noreply.github.com>
Co-authored-by: Qingyang Jiang <jiang131072@gmail.com>
Co-authored-by: co63oc <4617245+co63oc@users.noreply.github.com>
Co-authored-by: Kelly Guo <kellyg@nvidia.com>
Co-authored-by: Toni-SM <aserranomuno@nvidia.com>
Co-authored-by: njawale42 <njawale@nvidia.com>
Co-authored-by: zehao-wang <59912787+zehao-wang@users.noreply.github.com>
Co-authored-by: yijieg <yijieg@nvidia.com>
Co-authored-by: Yan Chang <yachang@nvidia.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: G.G <148413288+tkgaolol@users.noreply.github.com>
Co-authored-by: Philipp Reist <66367163+preist-nvidia@users.noreply.github.com>
Co-authored-by: Harsh Patel <hapatel@theaiinstitute.com>
Co-authored-by: James Tigue <jtigue@theaiinstitute.com>
Co-authored-by: rebeccazhang0707 <168459200+rebeccazhang0707@users.noreply.github.com>
Co-authored-by: michaellin6 <michalin@nvidia.com>
Co-authored-by: Huihua Zhao <huihuaz@nvidia.com>
Co-authored-by: Rafael Wiltz <rwiltz@nvidia.com>
Co-authored-by: Sergey Grizan <sgrizan@nvidia.com>
Co-authored-by: John <jaybdub@users.noreply.github.com>
Co-authored-by: yami007007 <weihuaz@nvidia.com>
Co-authored-by: Weihua Zhang <weihuaz@weihuaz-mlt.client.nvidia.com>
Co-authored-by: PeterL-NV <petliu@nvidia.com>
Co-authored-by: hougantc-nvda <127865892+hougantc-nvda@users.noreply.github.com>
Co-authored-by: peterd-NV <peterd@nvidia.com>
Co-authored-by: Cathy Li <40371641+cathyliyuanchen@users.noreply.github.com>
Co-authored-by: Louis LE LAY <le.lay.louis@gmail.com>
Co-authored-by: Javier Felix-Rendon <javierfelixrendon@gmail.com>
Co-authored-by: Doug Fulop <dougfulop@gmail.com>
Co-authored-by: Robin Vishen <117207232+vi7n@users.noreply.github.com>
Co-authored-by: -T.K.- <t_k_233@outlook.com>
Co-authored-by: Mayank Mittal <mittalma@leggedrobotics.com>
Co-authored-by: Rebecca Zhang <rebeccaz@nvidia.com>
Co-authored-by: Lorenz Wellhausen <lorenwel@users.noreply.github.com>
Co-authored-by: Lorenz Wellhausen <lorenz.wellhausen@rivr.ai>
Co-authored-by: Antoine RICHARD <antoiner@nvidia.com>
Co-authored-by: tifchen-nvda <tifchen@nvidia.com>
Co-authored-by: Cathy Li <yuanchenl@yuanchenl-mlt.client.nvidia.com>
Co-authored-by: rwiltz <165190220+rwiltz@users.noreply.github.com>
Co-authored-by: Milad-Rakhsha <miladrakhsha@gmail.com>
Co-authored-by: shauryadNv <shauryad@nvidia.com>
Co-authored-by: ndahile-nvidia <167997649+ndahile-nvidia@users.noreply.github.com>
Co-authored-by: matthewtrepte <mtrepte@nvidia.com>
Co-authored-by: yanziz-nvidia <yanziz@nvidia.com>
Co-authored-by: lotusl-code <lotusl@nvidia.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
gattra-rai
pushed a commit
to gattra-rai/IsaacLab
that referenced
this pull request
Nov 17, 2025
) We were incorrectly converting all numpy array data in the TiledCamera class into uint8 type warp arrays when simulation device is set to CPU. Some annotations like depth are float32 while segmentation data is uint32. The correct behavior should convert to warp arrays depending on the input data type of the numpy array. Additionally, rlgames configs were set to cuda device by default but were not being overridden when users specify the simulation device to CPU through cmdline. We should propagate the device setting to the rlgames configs so that we can run training on the same device, similar to how RSL RL is set up. Fixes isaac-sim#3526 - Bug fix (non-breaking change which fixes an issue) - [x] I have read and understood the [contribution guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html) - [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 <!-- 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 -->
koghalai123
pushed a commit
to koghalai123/IsaacLab
that referenced
this pull request
Dec 7, 2025
) # Description We were incorrectly converting all numpy array data in the TiledCamera class into uint8 type warp arrays when simulation device is set to CPU. Some annotations like depth are float32 while segmentation data is uint32. The correct behavior should convert to warp arrays depending on the input data type of the numpy array. Additionally, rlgames configs were set to cuda device by default but were not being overridden when users specify the simulation device to CPU through cmdline. We should propagate the device setting to the rlgames configs so that we can run training on the same device, similar to how RSL RL is set up. Fixes isaac-sim#3526 ## Type of change - Bug fix (non-breaking change which fixes an issue) ## Checklist - [x] I have read and understood the [contribution guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html) - [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 <!-- 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 -->
Edify0991
pushed a commit
to Edify0991/IsaacLab
that referenced
this pull request
Jan 14, 2026
) # Description We were incorrectly converting all numpy array data in the TiledCamera class into uint8 type warp arrays when simulation device is set to CPU. Some annotations like depth are float32 while segmentation data is uint32. The correct behavior should convert to warp arrays depending on the input data type of the numpy array. Additionally, rlgames configs were set to cuda device by default but were not being overridden when users specify the simulation device to CPU through cmdline. We should propagate the device setting to the rlgames configs so that we can run training on the same device, similar to how RSL RL is set up. Fixes isaac-sim#3526 ## Type of change - Bug fix (non-breaking change which fixes an issue) ## Checklist - [x] I have read and understood the [contribution guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html) - [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 <!-- 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 -->
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
We were incorrectly converting all numpy array data in the TiledCamera class into uint8 type warp arrays when simulation device is set to CPU. Some annotations like depth are float32 while segmentation data is uint32. The correct behavior should convert to warp arrays depending on the input data type of the numpy array.
Additionally, rlgames configs were set to cuda device by default but were not being overridden when users specify the simulation device to CPU through cmdline. We should propagate the device setting to the rlgames configs so that we can run training on the same device, similar to how RSL RL is set up.
Fixes #3526
Type of change
Checklist
pre-commitchecks with./isaaclab.sh --formatconfig/extension.tomlfileCONTRIBUTORS.mdor my name already exists there