Implement Fabric-aware get/set_local_poses via indexedfabricarray by pv-nvidia · Pull Request #2 · pv-nvidia/IsaacLab

pv-nvidia · 2026-05-05T11:07:06Z

Description

Adopts the prototype design from bareya/pbarejko/camera-update: all transform reads and writes go through wp.indexedfabricarray, the view→fabric mapping is path-based (no custom prim attributes), and FabricFrameView reads/writes omni:fabric:localMatrix directly.

Previously get_local_poses delegated to USD even when Fabric held the source-of-truth world matrices, so after set_world_poses() the next get_local_poses() returned stale values — the reason test_set_world_updates_local was marked xfail(strict=True). An earlier attempt fixed this by composing local = inv(parent_world) * child_world in torch using a Python-level USD parent loop, which was correct but 3× slower than USD. This PR replaces that with two Warp kernels operating on Fabric matrices via a parent indexed fabric array, eliminating the Python bottleneck.

Implementation summary

Three persistent PrimSelection instances (trans_ro, world_rw, local_rw) differing only in per-attribute access mode.
Path-based view→fabric index mapping computed from selection.GetPaths(); no isaaclab:view_index:HASH prim attributes written anywhere.
wp.indexedfabricarray everywhere: kernels dereference ifa[view_index] instead of taking a separate mapping argument.
Stage-level IFabricHierarchy cache + dirty-stages set: multiple FabricFrameView instances on the same stage share one hierarchy lookup.
Symmetric local↔world propagation via Warp kernels: set_local_poses marks the stage dirty; the next world read fires child_world = parent * child_local per child. Mirror kernel runs after set_world_poses to recompute child_local = inv(parent) * child_world.
Two new public Warp kernels in isaaclab.utils.warp.fabric: decompose_indexed_fabric_transforms and compose_indexed_fabric_transforms, plus propagation kernels update_indexed_local_matrix_from_world and update_indexed_world_matrix_from_local.

The shared contract test test_set_world_updates_local no longer needs the xfail override and passes for both cpu and cuda:0. Three additional tests cover the new paths: test_set_local_via_fabric_path, test_get_scales_fabric_path, test_prepare_for_reuse_detects_topology_change. Local run of the full fabric test suite: 41 passed, 0 failed.

Benchmark results

1024 prims, 50 iterations, NVIDIA RTX A6000.

Operation	USD (ms)	Fabric (ms)	Speedup
Get World Poses	13.5	0.067	201×
Set World Poses	30.0	0.123	244×
Interleaved Set→Get	43.8	0.159	276×
Get Local Poses	6.1	0.064	96×
Set Local Poses	8.6	0.053	163×

Reproduce with:

./isaaclab.sh -p scripts/benchmarks/benchmark_view_comparison.py \
  --num_envs 1024 --num_iterations 50 --backends usd fabric \
  --device cuda:0 --headless

Depends on: pv-nvidia:fix/fabric-prepare-for-reuse (PR #<TBD>) — please merge that one first.

Fixes #5

Type of change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)

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

Per the fragment-based changelog system (#5434), this PR ships fragments at source/isaaclab_physx/changelog.d/fabric-frame-view-local-poses.rst and source/isaaclab/changelog.d/pv-5381-rebased.rst instead of editing CHANGELOG.rst and config/extension.toml directly — the nightly CI workflow compiles those from the fragments.

…m#5473) # Description  Extend debug Visualization Markers, which are supported in the Kit Visualizer, to the Newton Visualizers. These Visualization Markers are various shapes and models which can be added to envs for debugging / showing extra information. Also added filtering for partial visualization (when we filtered which envs are shown the in the visualizer, we also filter the markers) For general USD mesh marker support in Newton, a followup PR will be required, once a Newton API for general USD -> Newton Mesh conversion is added (see newton-physics/newton#2667) Checked velocity arrows, dexcubes, raycasts, frames, goal markers  ## Type of change  - New feature (non-breaking change which adds functionality) - Documentation update ## Screenshots Please attach before and after screenshots of the change if applicable.  ## 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  --------- Signed-off-by: matthewtrepte <mtrepte@nvidia.com>

# Description - Increase the CI startup-hang grace period from 45s to 120s so slow but valid Kit startup is not killed prematurely. - Make `SurfaceGripper` fail fast on non-CPU simulation backends before loading the surface gripper extension. - Skip the CI-only `SurfaceGripperView` CPU initialization path that can deadlock, while keeping CUDA fail-fast coverage. ## 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 - [ ] 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

@kellyguo11

…isaac-sim#5478) Follow-up to isaac-sim#5434 (fragment-based changelog system). Two contributor-facing references still pointed at the old "edit CHANGELOG.rst directly" workflow: - **`docs/source/refs/contributing.rst`** — *Maintaining a changelog and extension.toml* section described per-version editing of CHANGELOG.rst with manual SemVer bumps. - **`.github/PULL_REQUEST_TEMPLATE.md`** — checklist asked contributors to update the changelog and bump extension.toml directly. Replaced only the parts that talk about direct editing; section/style guidance (Added/Changed/Deprecated/Removed/Fixed, past tense, the sample bullets themselves) stays intact. ## Test plan - [x] Pre-commit clean - [ ] Verify Build Latest Docs CI step renders the new section correctly cc @kellyguo11 — addresses the doc gaps flagged after isaac-sim#5434 merged.

# Description Mark all RTX-based rendering test cases flaky until they can produce deterministic low-res camera outputs that pass golden image testing on every CI run. Fixes # (issue)  ## Type of change - Test change ## Screenshots Please attach before and after screenshots of the change if applicable.  ## 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  --------- Signed-off-by: HuiDong Chen <huidongc@nvidia.com> Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

@pbarejko

…ic_write (isaac-sim#5380) ## Summary Replace the `sync_usd_on_fabric_write` workaround in `FabricFrameView` with proper `PrepareForReuse()` calls on the Fabric `PrimSelection`. This tells the renderer (FSD/Storm) that Fabric data has changed, so the next rendered frame reflects updated transforms — eliminating the need to copy Fabric writes back to USD. ## Motivation The existing `sync_usd_on_fabric_write` flag worked by mirroring every Fabric write back to USD, which defeated the performance benefits of Fabric. With `PrepareForReuse()`, the rendering pipeline is properly notified of Fabric data changes without any USD writeback. Additionally, the old code incorrectly fell back to USD for CPU devices — Warp handles CPU Fabric buffers correctly, so the fallback was unnecessary. This addresses two of the issues raised in @pbarejko Piotr's review of PR isaac-sim#4923: - **Issue #1** (USD write-back): Fabric writes no longer sync back to USD - **Issue isaac-sim#4** (PrepareForReuse): Renderer notification via `PrepareForReuse()` instead of USD writeback ## Changes ### Core (FabricFrameView) - Call `_prepare_for_reuse()` in write paths (`set_world_poses`, `set_scales`) to notify the renderer - Remove `sync_usd_on_fabric_write` parameter (accepted via `**kwargs` for backward compat) - Remove incorrect CPU/device fallback warnings — Warp handles CPU Fabric buffers correctly - Add `_rebuild_fabric_arrays()` for topology change recovery when `PrepareForReuse()` returns True, with assertion guarding the prim-count invariant ### Camera - Remove `sync_usd_on_fabric_write=True` from FrameView construction in `camera.py` ## Benchmark Results 1024 prims, 50 iterations, NVIDIA L40 GPU: | Operation | USD (ms) | Fabric (ms) | Speedup | |---|---|---|---| | Get World Poses | 14.71 | 0.07 | **203x** | | Set World Poses | 40.75 | 0.16 | **259x** | | Interleaved Set→Get | 55.90 | 0.24 | **232x** | | Get Local Poses | 11.08 | 11.12 | 1.0x | | Set Local Poses | 16.14 | 16.28 | 1.0x | Local poses fall back to USD (expected — Fabric only accelerates world poses via `omni:fabric:worldMatrix`). ## Tests Added | Test | What it validates | |------|------------------| | `test_camera_pose_update_reflected_in_render` | Camera pose changes propagate to rendered depth (close vs far) for CPU/GPU, tiled/non-tiled | | `test_fabric_set_world_does_not_write_back_to_usd` | Fabric writes stay in Fabric, USD prim unchanged | | `test_set_world_updates_local` (xfail) | Documents Issue isaac-sim#5: `set_world_poses` doesn't update local pose in Fabric mode | ## Test Results | Test Suite | Passed | Skipped | Xfailed | Total | |---|---|---|---|---| | Fabric contract tests (`test_views_xform_prim_fabric.py`) | 17 | 16 | 1 | 34 | | USD contract tests (`test_views_xform_prim.py`) | 45 | 0 | 0 | 45 | | Camera render test (`test_tiled_camera.py`) | 8 | 0 | 0 | 8 | ## Type of change - Performance improvement (removes redundant USD writeback on Fabric operations) ## 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 - [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 *No doc changes needed (parameter wasn't referenced in any docs)*

…tation (isaac-sim#5506) # Description This PR changes the PyTorch3d installation command in the locomanipulation SDG policy training / rollout to use git and install pytorch3d from source. Fixes # (issue) NV bug 6115836 ## Type of change  - Bug fix (non-breaking change which fixes an issue) ## Screenshots Please attach before and after screenshots of the change if applicable.  ## 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

# Description the camera config was importing `isaaclab_physx.renderers` because the default render_cfg was set to that config. this PR sets that to RendererConfig to remove the import, but provides a get_default_render_config method to the backend_utils to lazily import the config if needed. this is called __post_init__ on the camera config to replace the generic config as soon as possible to avoid downstream issues referencing the renderer config. this action can be moved to the factory if downstream references are cleaned up. ## Type of change - Refactor to remove imports in cfg class ## 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 --------- Co-authored-by: nvsekkin <72572910+nvsekkin@users.noreply.github.com>

…ields (isaac-sim#5275) # Description Splits IsaacLab's USD-physics cfg classes into solver-common base classes and backend-specific subclasses, and refactors the writers (`modify_*_properties`, `spawn_rigid_body_material`) so that schema application is data-driven rather than hard-coded per-class. Prepares the schema layer for multi-backend support (PhysX today, Newton/Mjc next) without polluting base classes with silently-ignored fields or stamping backend-specific schemas onto prims that didn't opt in. ## Architecture Two layered concepts: 1. **Per-declaring-class routing.** Each cfg field's USD namespace is determined by the class that declares it (walking the MRO). Base-class fields write under `physics:*`; subclass fields write under their own namespace (`physxRigidBody:*`, etc.). When a `PhysxRigidBodyPropertiesCfg` instance is written, base fields still go under `physics:*` because `_usd_namespace` is read from the declaring class via `__dict__`, not via `getattr` (which would hit the subclass override). 2. **Per-field exceptions.** Some "universal physics" fields have no USD path except through a backend-namespaced attribute today (e.g., `disable_gravity` only exists at `physxRigidBody:disableGravity`). These are declared as `_usd_field_exceptions = {applied_schema: (namespace, [fields...])}` on the base class; the writer applies the exception schema only when one of the listed fields is non-None. The single helper `_apply_namespaced_schemas(prim, cfg, cfg_dict)` in `schemas.py` does both passes for every writer (rigid body, collision, articulation root, joint drive, mesh collision, rigid-body material). ## Design constraints **One cfg class per spawner slot.** Spawners (`UsdFileCfg`, `MeshCuboidCfg`, etc.) carry a single field for each property group: `rigid_props: RigidBodyBaseCfg | None`, `collision_props: CollisionBaseCfg | None`, `joint_drive_props: JointDriveBaseCfg | None`, etc. The user cannot pass two cfgs into the same slot, so the cfg class hierarchy must be **single-rooted per spawner field** — one base class per group, with backend-specific subclasses below. This rules out a "PhysX cfg sits next to a Newton cfg as siblings" design and drives several placement decisions: | Constraint | Consequence | |---|---| | Universal-physics fields must be reachable from any backend's cfg | Goes on the **base** class, not a sibling backend cfg. Users on Newton-only deployments can use `RigidBodyBaseCfg(disable_gravity=True)` without importing `isaaclab_physx`. | | A PhysX-namespaced field whose semantics are universal (e.g., `disable_gravity`) | Lives on the base but routes to the PhysX namespace via `_usd_field_exceptions`. The base stays backend-clean; the writer dispatches the PhysX write only when the field is non-None. | | Writer logic must not branch on cfg subclass | Every writer is the same code path regardless of subclass. The cfg metadata (`_usd_namespace`, `_usd_applied_schema`, `_usd_field_exceptions`) drives behavior; the writer is a pure data interpreter. | | Adding a new backend (Newton, Mjc) | Requires a new subclass with its own `_usd_namespace` / `_usd_applied_schema`. No spawner-side changes, no writer-side changes, no base-cfg-side changes. | | A field has multiple USD paths today (one PhysX-namespaced, one Newton-namespaced) | Belongs on the **PhysX subclass**, not the base. A future `NewtonArticulationRootPropertiesCfg` will own the same conceptual field on the Newton side. ("Rule 2" — e.g., `enabled_self_collisions`.) | | A field has only one USD path today, namespaced under PhysX, but the conceptual quantity is universal | Belongs on the **base** with an `_usd_field_exceptions` entry. ("Rule 1" — e.g., `disable_gravity`, `articulation_enabled`, `contact_offset`, `rest_offset`, `max_joint_velocity`.) When Newton ships its own native attribute, the exception namespace switches transparently with no API change. | ## Field placement ### Base (solver-common) classes — `physics:*` namespace via `UsdPhysics.*API` | Cfg class | Field | USD attribute | |---|---|---| | `RigidBodyBaseCfg` | `rigid_body_enabled` | `physics:rigidBodyEnabled` | | `RigidBodyBaseCfg` | `kinematic_enabled` | `physics:kinematicEnabled` | | `CollisionBaseCfg` | `collision_enabled` | `physics:collisionEnabled` | | `MassPropertiesCfg` | `mass` | `physics:mass` | | `MassPropertiesCfg` | `density` | `physics:density` | | `RigidBodyMaterialBaseCfg` | `static_friction` | `physics:staticFriction` | | `RigidBodyMaterialBaseCfg` | `dynamic_friction` | `physics:dynamicFriction` | | `RigidBodyMaterialBaseCfg` | `restitution` | `physics:restitution` | | `JointDriveBaseCfg` | `drive_type` | `drive:<axis>:physics:type` | | `JointDriveBaseCfg` | `max_force` | `drive:<axis>:physics:maxForce` | | `JointDriveBaseCfg` | `stiffness` | `drive:<axis>:physics:stiffness` | | `JointDriveBaseCfg` | `damping` | `drive:<axis>:physics:damping` | | `MeshCollisionBaseCfg` | `mesh_approximation_name` | `physics:approximation` (token) | | `ArticulationRootBaseCfg` | `fix_root_link` | (synthesizes `UsdPhysics.FixedJoint`) | `JointDriveBaseCfg` and `MeshCollisionBaseCfg` use the typed `UsdPhysics.DriveAPI` / `UsdPhysics.MeshCollisionAPI` accessors at the writer level (multi-instance namespace and `TfToken` with `allowedTokens`, respectively); all other base fields flow through the helper's per-class routing. ### PhysX subclasses — `physx*:*` namespaces, `Physx*API` schemas | Cfg class | `_usd_namespace` | `_usd_applied_schema` | Adds fields | |---|---|---|---| | `PhysxRigidBodyPropertiesCfg` | `physxRigidBody` | `PhysxRigidBodyAPI` | `linear_damping`, `angular_damping`, `max_linear_velocity`, `max_angular_velocity`, `max_depenetration_velocity`, `max_contact_impulse`, `enable_gyroscopic_forces`, `retain_accelerations`, solver iter counts, sleep / stabilization thresholds | | `PhysxCollisionPropertiesCfg` | `physxCollision` | `PhysxCollisionAPI` | `torsional_patch_radius`, `min_torsional_patch_radius` | | `PhysxArticulationRootPropertiesCfg` | `physxArticulation` | `PhysxArticulationAPI` | `enabled_self_collisions`, solver iter counts, sleep / stabilization thresholds | | `PhysxJointDrivePropertiesCfg` | `physxJoint` | `PhysxJointAPI` | (currently empty; reserved for future PhysX-only knobs) | | `PhysxRigidBodyMaterialCfg` | `physxMaterial` | `PhysxMaterialAPI` | `compliant_contact_stiffness`, `compliant_contact_damping`, `friction_combine_mode`, `restitution_combine_mode` | | `PhysxConvexHullPropertiesCfg` | `physxConvexHullCollision` | `PhysxConvexHullCollisionAPI` | `hull_vertex_limit`, `min_thickness` | | `PhysxConvexDecompositionPropertiesCfg` | `physxConvexDecompositionCollision` | `PhysxConvexDecompositionCollisionAPI` | hull / voxel / shrink-wrap tunables | | `PhysxTriangleMeshPropertiesCfg` | `physxTriangleMeshCollision` | `PhysxTriangleMeshCollisionAPI` | `weld_tolerance` | | `PhysxTriangleMeshSimplificationPropertiesCfg` | `physxTriangleMeshSimplificationCollision` | `PhysxTriangleMeshSimplificationCollisionAPI` | `simplification_metric`, `weld_tolerance` | | `PhysxSDFMeshPropertiesCfg` | `physxSDFMeshCollision` | `PhysxSDFMeshCollisionAPI` | `sdf_margin`, `sdf_narrow_band_thickness`, `sdf_resolution`, etc. | ### `_usd_field_exceptions` table These fields are declared on a *base* class but the only USD path today goes through a non-base namespace. Each entry says: "if any listed field on this cfg is non-None, apply the exception schema and write that one attribute under the exception namespace." All other fields on the cfg follow the per-declaring-class routing rule. | Base cfg class | Exception schema | Namespace | Field(s) | Why on the base | |---|---|---|---|---| | `RigidBodyBaseCfg` | `PhysxRigidBodyAPI` | `physxRigidBody` | `disable_gravity` | Per-body gravity exclusion is universal physics; PhysX honors per-body, Newton consumes the same attribute via the bridge resolver (scene-level today; per-body fix is a Newton-side kernel change, not a cfg-API change) | | `CollisionBaseCfg` | `PhysxCollisionAPI` | `physxCollision` | `contact_offset`, `rest_offset` | Collision-pair generation distance and rest gap are universal physics; Newton importer consumes both via PhysX bridge to populate `Model.shape_collision_radius` / `_thickness` (`import_usd.py:2104, 2111`) | | `ArticulationRootBaseCfg` | `PhysxArticulationAPI` | `physxArticulation` | `articulation_enabled` | PhysX honors at sim time; IsaacLab Newton wrapper reads it as a spawn-time guard at `rigid_object.py:1035`. Universal user-facing intent | | `JointDriveBaseCfg` | `PhysxJointAPI` | `physxJoint` | `max_joint_velocity` | Sole USD path to `Model.joint_velocity_limit` in Newton (no `newton:*` equivalent today). The exception namespace switches transparently when Newton ships `newton:maxJointVelocity` as a registered applied API | When any exception field is non-None, the corresponding `Physx*API` schema is applied to the prim. When all exception fields are None, no PhysX schema is stamped — Newton-targeted prims authored from `*BaseCfg` stay free of PhysX schemas they didn't opt in to. ## Field renames (with deprecation aliases) To enforce the convention that python `snake_case` cfg field names map identity-style to USD `camelCase` attribute names, two legacy fields were renamed. Both keep the old name as a deprecation alias forwarded via `__post_init__` (emits `DeprecationWarning`, scheduled for removal in 5.0). | Old name | New name | USD attribute | |---|---|---| | `JointDriveBaseCfg.max_velocity` | `max_joint_velocity` | `physxJoint:maxJointVelocity` | | `JointDriveBaseCfg.max_effort` | `max_force` | `drive:<axis>:physics:maxForce` | ## Type of change - New feature (non-breaking change which adds functionality) - Breaking change (existing functionality will not work without user modification) The split is non-breaking at the spawner-cfg level — every base-class type accepts any subclass via polymorphism, and every legacy `RigidBodyPropertiesCfg` / `JointDrivePropertiesCfg` / `CollisionPropertiesCfg` / `ArticulationRootPropertiesCfg` / `MeshCollisionPropertiesCfg` / `RigidBodyMaterialCfg` / `FixedTendonPropertiesCfg` / `SpatialTendonPropertiesCfg` import path continues to work via deprecation-alias subclasses and `__getattr__` shims on `isaaclab.sim`, `isaaclab.sim.schemas`, and `isaaclab.sim.schemas.schemas_cfg`. Direct attribute access to the renamed fields still works through deprecation aliases. Removal scheduled for 5.0. The breaking aspect: cfg classes in `isaaclab_physx.sim.schemas` and `isaaclab_physx.sim.spawners.materials` are physically relocated. Anyone importing from internal paths (rather than `isaaclab.sim`) needs to update. ## Migration ```python # Before import isaaclab.sim as sim_utils rigid_props = sim_utils.RigidBodyPropertiesCfg(disable_gravity=True, linear_damping=0.1) joint_props = sim_utils.JointDrivePropertiesCfg(max_effort=80.0, max_velocity=5.0) collision_props = sim_utils.CollisionPropertiesCfg(contact_offset=0.02, torsional_patch_radius=1.0) material = sim_utils.RigidBodyMaterialCfg(static_friction=0.7, compliant_contact_stiffness=1000.0) # After (PhysX-targeted) import isaaclab.sim as sim_utils from isaaclab_physx.sim.schemas import ( PhysxRigidBodyPropertiesCfg, PhysxJointDrivePropertiesCfg, PhysxCollisionPropertiesCfg, ) from isaaclab_physx.sim.spawners.materials import PhysxRigidBodyMaterialCfg rigid_props = PhysxRigidBodyPropertiesCfg(disable_gravity=True, linear_damping=0.1) joint_props = PhysxJointDrivePropertiesCfg(max_force=80.0, max_joint_velocity=5.0) collision_props = PhysxCollisionPropertiesCfg(contact_offset=0.02, torsional_patch_radius=1.0) material = PhysxRigidBodyMaterialCfg(static_friction=0.7, compliant_contact_stiffness=1000.0) # After (Newton-targeted — base classes only, no PhysX schemas applied) from isaaclab.sim.schemas import RigidBodyBaseCfg, JointDriveBaseCfg, CollisionBaseCfg from isaaclab.sim.spawners.materials import RigidBodyMaterialBaseCfg rigid_props = RigidBodyBaseCfg(disable_gravity=True) # only base + exception fields available joint_props = JointDriveBaseCfg(max_force=80.0, max_joint_velocity=5.0) material = RigidBodyMaterialBaseCfg(static_friction=0.7) ``` Spawner type annotations remain unchanged — they accept any subclass via polymorphism. ## Internal helper ```python def _apply_namespaced_schemas(prim, cfg, cfg_dict): # 1. Per-field exceptions: pop listed fields, apply exception schema if any non-None, # write under exception namespace. # 2. Per-declaring-class routing: walk MRO to find each remaining field's owner class; # write under that class's _usd_namespace; apply that class's _usd_applied_schema. ``` Used by all five `modify_*_properties` writers and `spawn_rigid_body_material`. Replaced ~125 lines of duplicated gating logic with a single ~30-line helper. ## Side change: configclass `source/isaaclab/isaaclab/utils/configclass.py:_process_mutable_types` now detects string-form `ClassVar` annotations under PEP 563 (`from __future__ import annotations`) so it doesn't wrap `ClassVar[dict]` defaults in `field(default_factory=...)`. Matches Python stdlib `dataclasses` semantics. No pre-existing IsaacLab class used `ClassVar` inside a `@configclass` block, so the change has no effect on existing code; it enables the `ClassVar` metadata pattern this PR introduces. ## Test plan - [x] `test_schemas.py` (38 → 40 tests): all schema-cfg classes write correct attributes under the right namespace; PhysX schemas are NOT applied when only base/UsdPhysics fields are set; deprecation aliases (`max_velocity` → `max_joint_velocity`, `max_effort` → `max_force`) forward correctly and emit `DeprecationWarning`. **40 passed.** - [x] `test_schemas_shim.py`: legacy import paths (`isaaclab.sim.schemas.RigidBodyPropertiesCfg` etc.) resolve via `__getattr__` shims. **All passing.** - [x] `test_articulation.py`, `test_rigid_object_iface.py`, `test_valid_configs.py`, `test_spawn_*` — no regressions. - [x] Full suite (`./isaaclab.sh -t`): 8768/9205 pass, 437 unrelated baseline failures (rendering, `omni.physics.tensors.api` missing, OSC controller, `install_ci`, `pyglet`, Newton env-path, Anymal-C determinism). Zero new regressions; +123 passing tests vs. earlier state. - [x] `./isaaclab.sh -f` (pre-commit) clean. ## Supersedes Together with isaac-sim#5276, supersedes isaac-sim#4847 and isaac-sim#5203 with a cleaner schema-layer design. ## 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 (changelog fragments under `source/isaaclab/changelog.d/`) - [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 (fragment-based system) 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: ooctipus <zhengyuz@nvidia.com>

…c-sim#5301) Updates docs for using nurec background in locomanipulation sdg ## 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) - [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  --------- Co-authored-by: Kelly Guo <kellyg@nvidia.com>

Bumped packages: - isaaclab: 4.6.28 → 4.7.0 - isaaclab_newton: 0.5.26 → 0.6.0 - isaaclab_ov: 0.1.3 → 0.1.4 - isaaclab_ovphysx: 0.1.2 → 0.1.3 - isaaclab_physx: 0.5.29 → 0.6.0 - isaaclab_rl: 0.5.1 → 0.5.2 - isaaclab_tasks: 1.5.34 → 1.5.35 - isaaclab_teleop: 0.3.9 → 0.3.10

## Summary Bumps the Newton pin to [`v1.2.0rc2`](https://pypi.org/project/newton/1.2.0rc2/), which pulls in IsaacLab-relevant fixes plus the upstream tendon-scoping fix. ## What's new in Newton v1.2.0rc2 vs IsaacLab's current pin (`a27277e`) The current IsaacLab Newton pin is from late April; v1.2.0rc2 is the latest release-candidate cut. Notable fixes pulled in: - **[newton-physics/newton#2659](newton-physics/newton#2659 \"Scope USD custom-frequency parsing\" — `parse_usd` now scopes the custom-frequency walk to `root_path` natively. - **[newton-physics/newton#2678](newton-physics/newton#2678 Regression fix. - **[newton-physics/newton#2720](newton-physics/newton#2720 `SolverKamino` reset under `world_mask`. - **[newton-physics/newton#2710](newton-physics/newton#2710 VRAM leak fix on example reset. - Plus 16 other smaller fixes between rc1 and rc2. ## Required dep bumps Newton 1.2.0rc2's \`pyproject.toml\` requires: - \`warp-lang==1.13.0\` - \`mujoco==3.8.0\` (was 3.6.0) - \`mujoco-warp==3.8.0.1\` (was 3.6.0) Pins updated in: | File | Change | |---|---| | \`source/isaaclab/setup.py\` | \`warp-lang==1.12.0\` → \`==1.13.0\`; \`mujoco==3.6.0\` → \`==3.8.0\`; \`mujoco-warp==3.6.0\` → \`==3.8.0.1\` | | \`source/isaaclab_newton/setup.py\` | mujoco / mujoco-warp bumps; Newton pin → \`v1.2.0rc2\` | | \`source/isaaclab_visualizers/setup.py\` | 3× Newton pin → \`v1.2.0rc2\` | | \`tools/wheel_builder/res/python_packages.toml\` | All four pins mirrored | ## Code adapts \`warp-lang\` 1.13 removed the \`wp.math\` namespace. Two IsaacLab call sites use it: - \`source/isaaclab_newton/isaaclab_newton/physics/newton_manager.py:72\` - \`source/isaaclab_ov/isaaclab_ov/renderers/ovrtx_renderer_kernels.py:330\` Both rewritten as \`wp.math.transform_to_matrix(...)\` → \`wp.transform_to_matrix(...)\`. That's the only IsaacLab-side adapt needed. ## Test plan - [x] \`./isaaclab.sh -i newton\` clean install against the bumped pins. - [x] \`pip list\` confirms \`newton 1.2.0rc2\`, \`warp-lang 1.13.0\`, \`mujoco 3.8.0\`, \`mujoco-warp 3.8.0.1\`. - [x] Sanity smoke: Shadow-Hand-Over MAPPO (4 envs, 1 iter) runs clean — simulation init through CUDA graph capture through one training step + checkpoint save, no errors. - [x] Pre-commit clean. ## Caveat Smoke covered Shadow-Hand-Over MAPPO. Other envs with different sensors / renderers / collision setups could surface warp 1.13 or mujoco 3.8 differences the smoke didn't exercise; full PR CI catches them. --------- Co-authored-by: Kelly Guo <kellyg@nvidia.com>

Bumped packages: - isaaclab: 4.7.0 → 4.8.0 - isaaclab_mimic: 1.2.5 → 1.2.6 - isaaclab_newton: 0.6.0 → 0.7.0 - isaaclab_ov: 0.1.4 → 0.1.5 - isaaclab_physx: 0.6.0 → 0.6.1

# Description Clarifies the articulation joint friction API docs across the base, PhysX, and Newton implementations. The base API now warns that joint friction semantics are backend-specific. The PhysX docs distinguish legacy unitless coefficients from PhysX 5 static/dynamic friction efforts and viscous coefficients. The Newton docs now identify joint friction as an absolute force/torque value and include an MJWarp example mapping the value to MuJoCo Warp's `dof_frictionloss`. Fixes isaac-sim/IsaacLab-Internal#875 ## Type of change - Documentation update ## Screenshots Not applicable. ## Checklist - [ ] 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 (not applicable: docs-only change) - [x] I have added a changelog fragment under `source/<pkg>/changelog.d/` for every touched package (do **not** edit `CHANGELOG.rst` or bump `extension.toml` — CI handles that) - [x] I have added my name to the `CONTRIBUTORS.md` or my name already exists there

# Description Reduce higher-level dependency on packed state tensors in targeted IsaacLab call sites without changing existing task observation keys. This PR: - changes Pink IK to read `body_link_pose_w` directly instead of slicing `body_link_state_w`; - changes Dexsuite orientation rewards to use `root_link_quat_w` directly instead of slicing `root_state_w`; - adds explicit pick-place helpers for robot link pose and velocity; - keeps `get_all_robot_link_state()` available for compatibility, but marks it deprecated for removal in IsaacLab 4.0; - keeps existing `robot_links_state` task config entries unchanged. Fixes # (issue) ## Type of change - Bug fix (non-breaking change which fixes an issue) - Documentation update ## Screenshots N/A ## Test Plan - `./isaaclab.sh -p -m py_compile source/isaaclab/isaaclab/envs/mdp/__init__.pyi source/isaaclab/isaaclab/envs/mdp/actions/pink_task_space_actions.py source/isaaclab/isaaclab/envs/mdp/observations.py source/isaaclab_tasks/isaaclab_tasks/manager_based/manipulation/pick_place/mdp/__init__.pyi source/isaaclab_tasks/isaaclab_tasks/manager_based/manipulation/pick_place/mdp/observations.py source/isaaclab_tasks/isaaclab_tasks/manager_based/manipulation/dexsuite/mdp/rewards.py` - `./isaaclab.sh -f` - `git diff --check origin/develop..HEAD` - `rg -n "body_link_state_w|root_state_w" source/isaaclab/isaaclab/envs/mdp/actions/pink_task_space_actions.py source/isaaclab_tasks/isaaclab_tasks/manager_based/manipulation/pick_place/mdp/observations.py source/isaaclab_tasks/isaaclab_tasks/manager_based/manipulation/dexsuite/mdp/rewards.py` (no matches) - Existing/new MDP pytest not run locally. Per review, new MDP tests were removed and should be added in a separate PR. Local pytest collection is also blocked in this worktree because `./isaaclab.sh -p` selects `/usr/bin/python3.12` without `torch`. ## 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 - [ ] 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 Notes: - The unchecked warning item is intentional: this PR adds a `DeprecationWarning` to `get_all_robot_link_state()` so users can migrate before IsaacLab 4.0. - The unchecked test item follows review feedback: MDP tests should be added in a separate PR.

## Summary - Updated PhysX and Newton backend tests to use the current root-state, joint-state, contact-sensor, and wrench-composer API names. - Updated the Newton contact sensor adapter to use the current SensorContact constructor and force/metadata fields. - Bumped matching PhysX and Newton extension changelog/version files. ## Test Plan - [x] ./isaaclab.sh -p -m py_compile source/isaaclab_physx/test/sensors/test_frame_transformer.py source/isaaclab_newton/test/sensors/test_frame_transformer.py source/isaaclab_physx/test/sensors/test_contact_sensor.py source/isaaclab_newton/isaaclab_newton/physics/newton_manager.py source/isaaclab_newton/isaaclab_newton/sensors/contact_sensor/contact_sensor.py source/isaaclab_newton/isaaclab_newton/sensors/contact_sensor/contact_sensor_kernels.py - [x] ./isaaclab.sh -f - [x] Focused deprecation scan: 118 matches on origin/develop, 0 matches on this branch - [ ] Targeted GPU pytest on NvidiaWorkstation-WiFi: attempted in isaac-lab-base-pr5304:latest, but the PhysX container timed out after 3600s during pytest collection before tests ran

## Summary - Migrates core test and MDP callers off deprecated state/read/write helper APIs. - Updates the test_pose_inv tensor-to-NumPy conversion for NumPy 2.0. - Bumps the isaaclab changelog/version because core MDP source changed. ## Verification - ./isaaclab.sh -f - Scoped deprecated-call-site search: assigned core matches removed. Rebased onto develop after PR isaac-sim#5304 merged.

# Description Adds the missing core-concepts sensor documentation for the ground-truth PVA sensor and joint wrench sensor. The sensor overview now links both pages, the public `isaaclab.sensors` API page includes `Pva`, `PvaData`, and `PvaCfg`, and the sensor module table documents the joint wrench sensor prim-path expectation. Fixes isaac-sim/IsaacLab-Internal#880 Validation: - `./isaaclab.sh -f` - `git diff --check` - Verified `origin/develop` did not list `pva` or `joint_wrench_sensor` from `docs/source/overview/core-concepts/sensors/index.rst`, and this branch does. - Parsed the two new RST pages with `docutils` using local stubs for Sphinx-only directives and roles. - `make -C docs current-docs` was attempted locally but could not run because `sphinx-build` is not installed in this environment. ## Type of change - Documentation update ## Screenshots N/A; documentation text 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 - [ ] 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 added a changelog fragment under `source/<pkg>/changelog.d/` for every touched package (do **not** edit `CHANGELOG.rst` or bump `extension.toml` -- CI handles that) - [x] I have added my name to the `CONTRIBUTORS.md` or my name already exists there

isaac-sim#5538) ## Summary Two unrelated CI breakages on develop, bundled here so develop turns green in one PR. ### 1. Skip the failing viewergl test `test_cartpole_newton_visualizer_viewergl_rgb_motion[physx,newton]` started returning all-black frames on develop after `nvcr.io/nvidian/isaac-sim:latest-develop` flipped to a Kit 110.1.1 + USD 25.11 base. The failure has been deterministic across multiple PRs (isaac-sim#5523, isaac-sim#5495, isaac-sim#5408, …). Investigation so far has ruled out: - PR isaac-sim#5521 (revert in isaac-sim#5539 still failed) - Newton 1.0 → 1.2.0rc2 viewer code regression (only 7-line addition; ViewerGL alone yields 1.08M nonzero pixels) - warp 1.12 → 1.13 RegisteredGLBuffer ABI (byte-identical) - Module-load side effects of `isaaclab_physx.renderers` - CUDA-GL interop (PR isaac-sim#5540 diagnostic confirms direct CPU FBO readback also returns zeros, with `GL_NO_ERROR`) - GL context-currency (PR isaac-sim#5541 H6 attempt: still fails) - GL/CUDA sync (PR isaac-sim#5542 H4 attempt: still fails) Diagnostic output (PR isaac-sim#5540 v2): ``` [VIZDIAG] fbo=c_uint(8) pbo=None size=600x600 [VIZDIAG] glGetError before: GL_NO_ERROR [VIZDIAG] CPU-readback: nonzero=0/1080000 max=0 err=GL_NO_ERROR [VIZDIAG] PBO-result: nonzero=0/1080000 max=0 ``` The FBO itself is empty — Newton's pyglet/EGL renderer is not depositing pixels under Kit 110.1.1, even though `tiled_camera_rgb_non_black` (Kit RTX path) on the same env passes. Underlying root cause still being chased; this PR ships the skip to unblock develop. ### 2. Fix warp intersphinx 404 in docs build `https://nvidia.github.io/warp/objects.inv` started returning 404 — Warp's `objects.inv` only lives at `/stable/` and `/latest/` now. With Sphinx's `warnings_treated_as_errors`, the broken intersphinx fetch fails the docs build on every PR. Pinning to `/stable/` (matches the existing PyTorch `/docs/2.11/` workaround pattern in the same file). Verified `https://nvidia.github.io/warp/stable/objects.inv` returns 200. ## Test plan - [x] CI `isaaclab_visualizers` on this branch — was passing earlier with the skip; will re-verify with the bundled docs fix - [ ] CI `Build Latest Docs` on this branch — must turn green (was failing on every recent PR before this fix) ## Re-enable plan Once the underlying viewergl bug is identified and fixed, drop the `@pytest.mark.skip` decorator and remove the `jichuanh-disable-viewergl-flaky.skip` fragment.

# Description Replicates fk invalidation on other assets in Newton. Fixes isaac-sim#5359 ## Type of change - Bug fix (non-breaking change which fixes an issue) ## 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

## Summary - Migrates task/contrib camera callers from TiledCamera aliases to Camera. - Updates task state reads and in-hand write/target helper calls to explicit APIs. - Bumps task/contrib changelogs and extension versions for touched packages. ## Verification - ./isaaclab.sh -f - Scoped deprecated-call-site search: concrete task/contrib deprecated calls removed. Rebased onto develop after PR isaac-sim#5304 merged.

# Description Enabled OVRTX rendering tests on CI. `OVRTX 0.3` is not published yet, so we have to use `OVRTX 0.2` render output as golden images. Some of them are incorrect, I will update those images when we pin to `OVRTX 0.3`. Fixes # (issue)  ## Type of change  - 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.  ## 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

Summary - Fixes OvPhysX backend compatibility with the upcoming ovphysx 0.4 API by using `active_cuda_gpus` and explicit DirectGPU Carbonite settings when supported, while preserving the older `gpu_index` constructor path. - Fixes CPU-only OvPhysX tensor binding reads into GPU-backed articulation buffers. - Uses raw Warp buffers for OvPhysX articulation write views instead of `ProxyArray` wrappers. - Adds the `ovphysx` physics preset to the cartpole camera presets task. Validation - `./isaaclab.sh -f` - `./isaaclab.sh -p -m pytest source/isaaclab_ovphysx/test/assets/test_articulation_data.py source/isaaclab_ovphysx/test/assets/test_articulation.py` - `./isaaclab.sh -p scripts/reinforcement_learning/rsl_rl/train.py --task Isaac-Cartpole-Direct-v0 --num_envs 64 --max_iterations 2 --headless presets=ovphysx` - `./isaaclab.sh -p scripts/reinforcement_learning/rsl_rl/train.py --task Isaac-Ant-Direct-v0 --num_envs 64 --max_iterations 2 --headless presets=ovphysx` - `./isaaclab.sh -p scripts/reinforcement_learning/rsl_rl/train.py --task Isaac-Humanoid-Direct-v0 --num_envs 64 --max_iterations 2 --headless presets=ovphysx` - `./isaaclab.sh -p scripts/reinforcement_learning/rl_games/train.py --task=Isaac-Cartpole-Camera-Presets-Direct-v0 --num_envs=32 --max_iterations=2 --headless --enable_cameras presets=ovphysx,ovrtx_renderer,rgb` # Description This PR fixes several small IsaacLab-side issues needed for the OvPhysX backend to run the supported direct cartpole, ant, and humanoid tasks with the upcoming ovphysx 0.4 wheel. It also enables the cartpole camera presets task to select the `ovphysx` physics preset. The OvPhysX manager now detects the new constructor surface and passes explicit DirectGPU settings for GPU simulations. Older public wheels that still use `gpu_index` keep the previous constructor path. Fixes # (not applicable) ## Type of change - Bug fix (non-breaking change which fixes an issue) - New feature (non-breaking change which adds functionality) ## Screenshots Not applicable. ## 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 added a changelog fragment under `source/<pkg>/changelog.d/` for every touched package (do **not** edit `CHANGELOG.rst` or bump `extension.toml` — CI handles that) - [x] I have added my name to the `CONTRIBUTORS.md` or my name already exists there

# Description Adds a dedicated Newton experimental tutorial for using the Kamino solver. The page explains that Kamino is selected through a Newton physics solver preset, shows the task changes needed to add a `kamino` preset, lists compatibility checks for assets, resets, sensors, and renderers, and documents the Kamino-specific solver parameters by category. This addresses Kellys follow-up request on isaac-sim#5457 for a tutorial describing what needs to change to work with Kamino and for descriptions of Kamino-specific solver parameters. Fixes # (issue) ## Type of change - Documentation update ## Screenshots Not applicable. Documentation-only RST change. ## 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 - [ ] 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 extensions `config/extension.toml` file - [x] I have added my name to the `CONTRIBUTORS.md` or my name already exists there Notes: - Ran `./isaaclab.sh -f` successfully. - Verified the `literalinclude` target and referenced labels locally. - `./isaaclab.sh -d` could not start in this checkout because there is no virtual environment and system Python is PEP 668 protected, so pip refused to install docs requirements. Because Sphinx did not run, the warning checklist item is intentionally left unchecked. - No tests or changelog fragment were added because this is a documentation-only follow-up under `docs/source`; the current repository guidance uses `source/<pkg>/changelog.d` fragments only for touched source packages.

…a.pos (isaac-sim#5547)

…ty and position controllers (isaac-sim#3895) ## Description This PR extends [3760](isaac-sim#3760) by introducing a navigation tasks for the ARL robot. The PR adds a confined cluttered environment, adds acceleration, velocity and position controllers + configs, extends the MDP and RL configs and adds a Variational Auto Encoder to generate image latents for observations. The PR depends on the `MultiMeshRayCasterCamera` introduced in PR [3298](isaac-sim#3298) (currently not merged in IsaacLab). ## Changes ### Type of Change - New feature (non-breaking change which adds functionality) - Documentation update (added docs/comments where applicable) ### Files changed (high-level summary) - New files added: - source/isaaclab_tasks/isaaclab_tasks/manager_based/drone_arl/navigation/* (new task code and config, obstacle scene code and config) - source/isaaclab_tasks/isaaclab_tasks/manager_based/drone_arl/mdp/vae_model.pt - source/isaaclab/isaaclab/controllers/lee_acceleration_control_cfg.py - source/isaaclab/isaaclab/controllers/lee_acceleration_control.py - source/isaaclab/isaaclab/controllers/lee_velocity_control_cfg.py - source/isaaclab/isaaclab/controllers/lee_velocity_control.py - source/isaaclab/isaaclab/controllers/lee_position_control_cfg.py - ource/isaaclab/isaaclab/controllers/lee_position_control.py - Modified: - source/isaaclab_tasks/isaaclab_tasks/manager_based/drone_arl/mdp/* (added navigation specifics) - source/isaaclab/isaaclab/envs/mdp/actions/actions_cfg.py (added new action config) - source/isaaclab/isaaclab/envs/mdp/actions/thrust_actions.py (introduced new navigation action handling controller application) - Total diff (branch vs main, includes also unmerged changes of PR [3760](isaac-sim#3760) and PR [3298](isaac-sim#3298)): 74 files changed, 8029 insertions, 88 deletions ## Dependencies - The new drone task references standard repo-internal packages and Isaac Sim; no external pip packages required beyond the repo standard. ## 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: Grzegorz Malczyk <44407007+grzemal@users.noreply.github.com> Signed-off-by: renezurbruegg <zrene@ethz.ch> Signed-off-by: Welf Rehberg <65718465+Zwoelf12@users.noreply.github.com> Co-authored-by: grzemal <grzegorz.malczyk@ntnu.no> Co-authored-by: Grzegorz Malczyk <44407007+grzemal@users.noreply.github.com> Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com> Co-authored-by: René zurbrügg <zrene@ethz.ch> Co-authored-by: Pascal Roth <roth.pascal@outlook.de> Co-authored-by: Pascal Roth <57946385+pascal-roth@users.noreply.github.com>

…5564) # Description When benchmarking scripts are executed with num_iterations set to below the threshold for reward logging, the run can produce missing reward data. However, the scripts are hardcoded to always parse rewards from tensorboard, which may not exist in these cases. This change patches the RL benchmarking scripts to only process rewards logging if they were written to tensorboard. ## 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 - [ ] 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

# Description  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)  ## Type of change  - Documentation update ## Screenshots Please attach before and after screenshots of the change if applicable.  ## 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

# Description  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)  ## Type of change  - 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.  ## 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

This PR improves IsaacLab Teleop retargeting performance and installation reliability. - Added configurable IsaacTeleop retargeting execution via `IsaacTeleopCfg.retargeting_execution`. - Enabled deadline-paced pipelined retargeting by default, so IsaacTeleop retargeting work can overlap with Isaac Lab simulation stepping. - Preserved synchronous retargeting as an opt-in mode for exact current-frame behavior. - Added an extension-level `pip_upgrade_dependencies` setting in `extension.toml` so `./isaaclab.sh --install` can explicitly upgrade selected `install_requires` dependencies after editable install. - Used that mechanism for `isaaclab_teleop` to upgrade to the latest compatible `isaacteleop` without duplicating the version spec outside `setup.py`. ## Why The pipelined retargeting path reduces Python-side frame pressure by returning the latest completed retargeting output while the current frame is submitted in parallel. The install change fixes CI/local environments where an older compatible `isaacteleop` version is already installed. Since `pip install -e source/isaaclab_teleop` does not upgrade already-satisfied dependencies by default, which could keep using a stale IsaacTeleop package. The new targeted upgrade keeps the version range in `setup.py` as the source of truth while still allowing the install command to refresh `isaacteleop`. # Description  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)  ## Type of change  - New feature (non-breaking change which adds functionality) ## Screenshots Please attach before and after screenshots of the change if applicable.  ## 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

# Description Adds the **Assemble Trocar** manipulation task for the Unitree G1 (29-DoF + Dex3), with RLinf support. Key additions: - **Task MDP**: observations (body + Dex3 joint states), reward functions (4-stage sparse), termination conditions (timeout, success, object drop), and reset events (scene reset, task stage reset, random tray rotation). - **Camera presets**: front camera and left/right wrist cameras (TiledCamera, 224×224) configured for GR00T visual input. - **Robot presets**: G1 29-DoF + Dex3 articulation configuration. - **GR00T data config**: `IsaacLabDataConfig` defining video/state/action modality keys, transforms (SinCos state encoding, min-max action normalization, color jitter), and model-specific settings. - **RLinf extension update**: minor update to `isaaclab_contrib/rl/rlinf/extension.py` to support the new task registration. ## Type of change - New feature (non-breaking change which adds functionality) ## 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>

…aac-sim#5276) # Description Adds Newton-native and MuJoCo-specific schema cfg classes to `isaaclab_newton.sim.schemas`, following the base/subclass framework from isaac-sim#5275. All new cfgs use the per-declaring-class MRO routing in `_apply_namespaced_schemas` — no backend-specific branching in any writer. Depends on isaac-sim#5275. ## New cfgs ### MuJoCo (Newton MuJoCo kernel, `mjc:*` namespace) | Class | Field | USD attribute | Applied schema | |---|---|---|---| | `MujocoRigidBodyPropertiesCfg` | `gravcomp` | `mjc:gravcomp` | None (raw attr) | | `MujocoJointDrivePropertiesCfg` | `actuatorgravcomp` | `mjc:actuatorgravcomp` | `MjcJointAPI` | Body-level `gravcomp` must be set for joint-level `actuatorgravcomp` to have any effect. The spawner auto-enables `MujocoRigidBodyPropertiesCfg(gravcomp=1.0)` when joint-level actuator gravcomp is requested without body-level gravcomp. ### Newton-native (`newton:*` namespace) | Class | Fields | USD attributes | Applied schema | |---|---|---|---| | `NewtonCollisionPropertiesCfg` | `contact_margin`, `contact_gap` | `newton:contactMargin`, `newton:contactGap` | `NewtonCollisionAPI` | | `NewtonMeshCollisionPropertiesCfg` | `max_hull_vertices` | `newton:maxHullVertices` | `NewtonMeshCollisionAPI` | | `NewtonMaterialPropertiesCfg` | `torsional_friction`, `rolling_friction` | `newton:torsionalFriction`, `newton:rollingFriction` | `NewtonMaterialAPI` | | `NewtonArticulationRootPropertiesCfg` | `self_collision_enabled` | `newton:selfCollisionEnabled` | `NewtonArticulationRootAPI` | ## Design constraints Same single-cfg-per-spawner-slot rule as isaac-sim#5275. Newton cfgs subclass the same base classes as PhysX cfgs; each declares `_usd_namespace`/`_usd_applied_schema` (ClassVar) and fields that auto-camelCase to their USD attr names. Per-declaring-class MRO routing handles mixed PhysX+Newton cfg hierarchies correctly. ## Field renames (with deprecation aliases through 5.0) | Old | New | Reason | |---|---|---| | `gravity_compensation_scale` | `gravcomp` | Single word identity: `gravcomp` → `mjc:gravcomp` | | `gravity_compensation` | `actuatorgravcomp` | Single word identity: `actuatorgravcomp` → `mjc:actuatorgravcomp` | ## Type of change - New feature (non-breaking) Forwarding shims on `isaaclab.sim.schemas` keep existing imports working. Deprecation aliases keep old field names working through 5.0. ## Test plan - [x] MuJoCo tests: `mjc:gravcomp` / `mjc:actuatorgravcomp` written when set, not written when None - [x] Newton collision, material, articulation-root: attrs written, schemas applied only when non-None - [x] Deprecation alias tests for renamed fields - [x] `test_schemas.py` 46/46 pass — no regressions - [x] Pre-commit clean ## Supersedes Together with isaac-sim#5275, supersedes isaac-sim#4847 and isaac-sim#5203. --------- Co-authored-by: Kelly Guo <kellyg@nvidia.com> Co-authored-by: Antoine RICHARD <antoiner@nvidia.com>

Bumped packages: - isaaclab: 5.0.0 → 5.1.0 - isaaclab_assets: 0.3.3 → 0.3.4 - isaaclab_contrib: 0.3.1 → 0.3.2 - isaaclab_experimental: 0.0.3 → 0.0.4 - isaaclab_newton: 0.7.2 → 0.8.0 - isaaclab_ov: 0.1.6 → 0.1.7 - isaaclab_tasks: 1.5.36 → 1.5.37 - isaaclab_teleop: 0.3.10 → 0.3.11

## Summary - ``docs/source/setup/ecosystem.rst``: ``https://robosuite.ai/`` now returns 404. Updated the RoboSuite reference link to the project's GitHub repo (``https://github.com/ARISE-Initiative/robosuite``). - ``docs/source/how-to/cloudxr_teleoperation.rst``: ``https://github.com/NVIDIA/IsaacTeleop/blob/main/src/plugins/manus/README.md`` is gone (404). The IsaacTeleop repo root still resolves, so the Manus plugin reference now points there until the upstream doc is republished. These were the two failures from the ``Documentation Links`` CI job; everything else lychee reported was a 301/302 redirect already in the accept list. ## Test plan - [x] ``pre-commit run --files docs/source/how-to/cloudxr_teleoperation.rst docs/source/setup/ecosystem.rst`` — passes. - [ ] Re-run ``Documentation Links`` on the PR — expect zero ``[ERROR]`` entries. Signed-off-by: Kelly Guo <kellyg@nvidia.com> Co-authored-by: Kelly Guo <kellyg@nvidia.com>

…pers (isaac-sim#5579) ## Summary `FabricNoticeBindings.initialize` and `CubricBindings.initialize` retried `tryAcquireInterfaceWithClient` with `clientName=None` when the first attempt returned null. Carbonite has rejected null client names since 2018, so the retry only emitted: ``` [Error][carb] Client passed into the framework is nullptr. ``` and always returned null. This surfaces in any IsaacLab run that touches Carbonite outside a full Kit context — for example, a remote asset path that pulls in `omni.client` (and therefore a partial Carb framework) before `_isaac_sim` is loaded. ## Changes - Removed the `tryAcquire(None, ...)` fallback in both helpers. - Replaced the first-attempt client name `"carb.scripting-python.plugin"` with the same identity each helper already passes to `acquireFramework`: `"isaaclab.cloner"` and `"isaaclab.cubric"`. Refcount tracking is now attributed to IsaacLab rather than to Kit's Python scripting host. `clientName` is not used by Carbonite to gate interface lookup — any non-null string is accepted — so the in-Kit success path is byte-for-byte equivalent and the cloning speedup (Fabric notice listener suspension) is preserved. ## Test plan - [x] `./isaaclab.sh -f` clean on both commits. - [x] Confirmed locally that removing the null fallback removes the `[Error][carb]` log line in the repro that triggered this (rc41 + Ant remote asset path, no Kit loaded). - [ ] Smoke test a normal in-Kit cloning run (e.g. any Newton/PhysX env with `num_envs >= 64`) and confirm `Cloner.clone()` wall-time is unchanged before vs after this PR.

# Description This PR enables heterogeneous dexsuite with newton backend Fixes # (issue)  ## Type of change  - 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.  ## 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

# Description Reverts CI image to previous Isaac Sim image from 05/11 as the new image is causing timeouts in our CI. TODO: investigate failing cause of the new image. ## 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 - [ ] 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

Bumped packages: - isaaclab: 5.1.0 → 5.1.1 - isaaclab_newton: 0.8.0 → 0.8.1 - isaaclab_ov: 0.1.7 → 0.1.8 - isaaclab_physx: 0.6.3 → 0.6.4 - isaaclab_tasks: 1.5.37 → 1.5.38

# Description Fixes partial migration of metadata access in isaac-sim#5418  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)  ## Type of change  - 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.  ## 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  --------- Co-authored-by: Kelly Guo <kellyg@nvidia.com>

@marcodiiga

## Summary Implements `RigidObject` and `RigidObjectData` for the OVPhysX backend (issue isaac-sim#5316), satisfying the `BaseRigidObject` and `BaseRigidObjectData` contracts. Mirrors the PhysX `RigidObject` and the existing OVPhysX `Articulation` patterns; runs kitless via the standard `SimulationContext` + `UsdFileCfg(usd_path=…)` pipeline. - New: `source/isaaclab_ovphysx/isaaclab_ovphysx/assets/rigid_object/{rigid_object.py, rigid_object_data.py, __init__.py, __init__.pyi}` (~1900 lines). - New: `source/isaaclab_ovphysx/isaaclab_ovphysx/assets/kernels.py` — shared Warp kernels relocated from `articulation/kernels.py` so both asset types use them; new `_compose_root_link_pose_from_com` for COM→link write conversion; ported Newton's `derive_body_acceleration_from_body_com_velocities` to FD acceleration locally (no wheel `RIGID_BODY_ACCELERATION` dependency). - New `RIGID_BODY_*` `TensorType` aliases in `isaaclab_ovphysx/tensor_types.py` — six already-shipping types as direct imports, three forward-compat aliases (`ACCELERATION`, `INV_MASS`, `INV_INERTIA`) gated by `try/except AttributeError` so the module loads cleanly today. - Allegro env hookup (`source/isaaclab_tasks/.../allegro_hand/allegro_hand_env_cfg.py`): adds `ovphysx` variants to `ObjectCfg` and `PhysicsCfg`, mirroring the Cartpole/Ant pattern. Enables running `Isaac-Repose-Cube-Allegro-Direct-v0` against OVPhysX via `./scripts/run_ovphysx.sh`. - Cross-backend interface tests: `BACKENDS.append(\"ovphysx\")` + `create_ovphysx_rigid_object` factory in `source/isaaclab/test/assets/test_rigid_object_iface.py`. - Versioning: `isaaclab_ovphysx 0.1.2 → 0.2.0`, `isaaclab_tasks 1.5.29 → 1.5.30`. ## Test plan ### Real-backend rigid-object tests (kitless, via `run_ovphysx.sh`) ``` ./scripts/run_ovphysx.sh -m pytest source/isaaclab_ovphysx/test/assets/test_rigid_object.py -v ``` Current state: **61 passed, 14 xfailed**. The 61 passing tests are real-backend (live `ovphysx.PhysX` instance, real `TensorBinding` reads, real sim steps) — port of the PhysX `test_rigid_object.py` structure with the canonical `SimulationContext` + `UsdFileCfg(ISAAC_NUCLEUS_DIR/Props/Blocks/DexCube/dex_cube_instanceable.usd)` pattern Cartpole/Newton already use. Catches two production bugs the previous mock-based suite missed (\`hasattr\` swallow on \`body_names\`, \`self._device\` always falling back to \`cuda:0\`). ### Cross-backend interface tests ``` ./scripts/run_ovphysx.sh -m pytest source/isaaclab/test/assets/test_rigid_object_iface.py -v -k ovphysx ``` Current state: **252 passed, 120 fixed shape-mismatch failures fixed in this branch** (4 distinct bugs caught: full-write row-count guard, 1-D mask src normalization, COM-pose row-count guard, two unimplemented \`default_root_pose/vel\` stubs). ### Existing articulation regression check ``` ./scripts/run_ovphysx.sh -m pytest source/isaaclab_ovphysx/test/assets/test_articulation.py source/isaaclab_ovphysx/test/assets/test_articulation_data.py -v ``` Verifies the kernel relocation in Task 2 didn't break existing articulation tests. Recommended before merge. ### Manual end-to-end (Kit + Nucleus) \`Isaac-Repose-Cube-Allegro-Direct-v0\` with the new \`ovphysx\` preset — manual smoke test (Kit-required, requires Nucleus access): ``` ./scripts/run_ovphysx.sh source/isaaclab_tasks/isaaclab_tasks/direct/allegro_hand/allegro_hand_env.py --num_envs 4 --headless ``` ## Wheel-side gaps (for @marcodiiga) The 14 remaining xfails split as follows; only **10 are wheel-side blockers** (all in the same category): | Category | xfailed | Owner | |---|---|---| | Material-properties API (`RIGID_BODY_MATERIAL` TensorType or view helper) | 10 | Wheel — see [docs/superpowers/specs/2026-04-28-ovphysx-wheel-gaps-for-marco.md](https://github.com/AntoineRichard/IsaacLab/blob/antoiner/feat/ovphysx_rigidobject/docs/superpowers/specs/2026-04-28-ovphysx-wheel-gaps-for-marco.md) for the proposed contract | | `test_initialization_with_no_rigid_body` (RuntimeError on missing prim) | 2 | IsaacLab follow-up — error-handling polish | | `test_initialization_with_articulation_root` (out-of-scope per spec) | 2 | IsaacLab follow-up — explicit \`NotImplementedError\` stub | Three additional wheel-side `RIGID_BODY_*` TensorTypes (`ACCELERATION`, `INV_MASS`, `INV_INERTIA`) are forward-compat — declared via `try/except AttributeError` aliases on the IsaacLab side, no IsaacLab consumers depend on them today, but they auto-activate when the wheel ships them. ## Notes - IsaacLab side is wheel-update-agnostic: `tensor_types.py` defensive aliases let \`isaaclab_ovphysx\` import cleanly against today's \`ovphysx 0.3.7\`. - Local docs at \`docs/superpowers/specs/\` (gitignored) include the original design spec, the corrected Marco-feedback gap spec, and the test-gaps follow-up. - Branch contains 30 commits including Marco's contract corrections (renames \`RIGID_BODY_ROOT_POSE\` → \`RIGID_BODY_POSE\`, \`MASS\` shape \`(N, 1)\` → \`(N,)\`). --------- Co-authored-by: Kelly Guo <kellyg@nvidia.com>

…5400) ## 1. Summary Make IK / OSC / RMPFlow task-space controllers backend-agnostic so Franka manipulation envs run under Newton. The action terms previously called PhysX-only methods on `asset.root_view` directly, which crashed under Newton with `AttributeError`. The Franka reach envs worked around this by hardcoding `self.sim.physics = PhysxCfg(...)` with the comment *"{IK,OSC} control is not supported with Newton physics; use PhysX only"*. This PR removes that workaround. End-to-end result: `Isaac-Reach-Franka-{IK-Abs,IK-Rel,OSC}-v0` run on either backend, picked via `presets=newton`. ## 2. Design Four new properties on `BaseArticulationData`: - `body_link_jacobian_w` — geometric Jacobian, linear rows at the link origin (USD prim frame). What IK / OSC consumers want. - `body_com_jacobian_w` — geometric Jacobian, linear rows at the center of mass. Engine-natural form; useful for dynamics reasoning. - `mass_matrix` — joint-space generalized mass matrix `M(q)`. - `gravity_compensation_forces` — joint-space gravity-loading torques `g(q)`. Plus one metadata property on `BaseArticulation`: - `num_base_dofs` — number of free DoFs of the floating base. `0` for fixed-base, `6` for floating-base. Maps an actuated-joint id `j` to its column in J / M / g via `j + num_base_dofs`. All four data properties are concrete-with-`NotImplementedError` defaults; backends override what they support. ### 2.1 DoF axis: `num_joints + num_base_dofs` (industry-standard) The DoF axis prepends `num_base_dofs` columns at the front of the joint axis: `0` for fixed-base, `6` for floating-base. The 6 columns are the floating-base spatial velocity in world frame, ordered `[lin_x, lin_y, lin_z, ang_x, ang_y, ang_z]`. This matches every major rigid-body library: | Library | Floating-base layout | |---------|----------------------| | Pinocchio | Free-flyer joint contributes 6 to `nv`; reduced-coordinate `nv = 6 + n_actuated`. `pinocchio::computeJointJacobians` writes `(6, nv)`. | | Drake | `MultibodyPlant` ephemeral floating joint; `MultibodyPlant::CalcJacobianSpatialVelocity` returns `(6, nv)` with leading 6 free-floating cols. | | MuJoCo | `<freejoint/>` introduces 6 DoFs at the front of `qvel`; `mj_jac*` returns `(_, nv)`. | | RBDL | `JointTypeFloatingBase` adds 6 to `dof_count`; `CalcPointJacobian` returns `(_, dof_count)`. | | OCS2 | `generalizedCoordinatesNum = 6 + actuatedJointsNum` for floating-base robots. | | iDynTree | `getFreeFloatingMassMatrix` returns `(6 + dofs, 6 + dofs)`. | Consumers operating in actuated-joint space (action terms keyed by `joint_ids`) compute `[j + asset.num_base_dofs for j in joint_ids]` once at init — same application-level reduction as every surveyed library. ### 2.2 Output shapes by backend Concrete shapes for each engine output and the wrapper transform applied. `N` = num_instances, `B` = num_bodies (full count incl. root), `J` = num_joints (actuated only). "Default" is the engine-native per-view shape (post-gather). "passthrough" = wrapper applies no shape change. The COM→origin shift is values-only (does not change shape). | Property | Base | Newton (default ⟶ transform) | PhysX (default ⟶ transform) | Aligned | |---|---|---|---|---| | `body_link_jacobian_w` | fixed | `(N, B, 6, J)` ⟶ drop fixed-root row + COM→origin shift | `(N, B−1, 6, J)` ⟶ COM→origin shift | `(N, B−1, 6, J)` | | `body_link_jacobian_w` | floating | `(N, B, 6, J+6)` ⟶ COM→origin shift | `(N, B, 6, J+6)` ⟶ COM→origin shift | `(N, B, 6, J+6)` | | `body_com_jacobian_w` | fixed | `(N, B, 6, J)` ⟶ drop fixed-root row | `(N, B−1, 6, J)` ⟶ passthrough | `(N, B−1, 6, J)` | | `body_com_jacobian_w` | floating | `(N, B, 6, J+6)` ⟶ passthrough | `(N, B, 6, J+6)` ⟶ passthrough | `(N, B, 6, J+6)` | | `mass_matrix` | fixed | `(N, J, J)` ⟶ passthrough | `(N, J, J)` ⟶ passthrough | `(N, J, J)` | | `mass_matrix` | floating | `(N, J+6, J+6)` ⟶ passthrough | `(N, J+6, J+6)` ⟶ passthrough | `(N, J+6, J+6)` | | `gravity_compensation_forces` | fixed | (no upstream primitive) ⟶ `NotImplementedError` | `(N, J)` ⟶ passthrough | `(N, J)` | | `gravity_compensation_forces` | floating | (no upstream primitive) ⟶ `NotImplementedError` | `(N, J+6)` ⟶ passthrough | `(N, J+6)` | The aligned column collapses across base type using two derived symbols: - `num_base_dofs` = `0` fixed | `6` floating — exposed as `BaseArticulation.num_base_dofs` - `num_jacobi_bodies` = `B − 1` fixed | `B` floating — fixed-root row excluded for fixed-base | Property | Aligned (generalized) | |---|---| | `body_link_jacobian_w`, `body_com_jacobian_w` | `(N, num_jacobi_bodies, 6, J + num_base_dofs)` | | `mass_matrix` | `(N, J + num_base_dofs, J + num_base_dofs)` | | `gravity_compensation_forces` | `(N, J + num_base_dofs)` | Two observations: 1. The only body-axis asymmetry is **Newton's fixed-base Jacobian**: Newton's `eval_jacobian` includes a zero row for the fixed-root joint that the wrapper drops. PhysX's engine already drops it. 2. The DoF axis is in the industry-standard `J + num_base_dofs` form on both engines natively. The only DoF-axis asymmetry is `gravity_compensation_forces` (Newton NIE pending upstream primitive). ### 2.3 Why on `BaseArticulationData`, not `BaseArticulation` `BaseArticulationData` already exposes per-body / per-joint state as cached lazy `@property` accessors with `TimestampedBuffer` invalidation (`body_link_pose_w`, `joint_pos`, etc.). The four new accessors fit the same shape — read-only state indexed by body / joint, refreshed per sim step — so they reuse that infrastructure and let consumer code stay symmetric: ```python # IK action term ee_pose = articulation.data.body_link_pose_w.torch[:, ee_idx] ee_jac = articulation.data.body_link_jacobian_w.torch[:, ee_jac_idx] # same prefix ``` ## 3. Fixed: latent PhysX IK / OSC frame mismatch PhysX's `_root_view.get_jacobians()` returns linear rows referenced at each body's **center of mass**, not the link origin. Undocumented behavior — verified empirically by bypassing the IsaacLab wrapper and confirming `J · q̇` matches `body_com_lin_vel_w` to 1e-8 and differs from `body_link_lin_vel_w` by exactly `ω × r_com_world` (the rigid-body shift). The PhysX data layer already encoded this convention for velocities: `body_com_vel_w` is the raw passthrough of `_root_view.get_link_velocities()`; `body_link_vel_w` is **derived** via a shift kernel. Before this PR, IK / OSC / RMPFlow action terms on PhysX consumed `_root_view.get_jacobians()` directly while using `data.body_link_pose_w` as the EE pose setpoint. The frame mismatch contributes `ω × r_com_world` per body to the linear-row contract — undetected in CI because no existing test compared `J · q̇` against `body_link_lin_vel_w` directly. The new contract test `test_get_jacobians_link_origin_contract` parametrized to `anymal` catches it explicitly: 0.32 m/s residual on PhysX without the fix. After this PR, PhysX's `body_link_jacobian_w` applies the same COM→origin shift kernel that Newton uses, mirroring the existing `body_link_vel_w` derivation. Both backends now satisfy `body_link_jacobian_w · q̇ == body_link_vel_w` to numerical precision (test tolerance 5e-3 absolute, 1e-2 relative). The COM-referenced sibling `body_com_jacobian_w` is exposed for callers that intentionally want the engine-native form (e.g. dynamics-side reasoning at the COM). Also: the three PhysX passthrough properties (`body_com_jacobian_w`, `mass_matrix`, `gravity_compensation_forces`) now pin a single `ProxyArray` in `_create_buffers` instead of allocating one per property read. PhysX tensor-view getters return pointer-stable buffers for the articulation's lifetime — verified manually across `sim.step`, a manual joint write, and `sim.reset`. ## 4. Newton-side details ### 4.1 Pre-allocation for capture safety Dynamics-scratch allocation is grouped in a private `ArticulationData._create_jacobian_buffers(model)` helper called from `_create_buffers`. The helper is sectioned by which property each buffer feeds, and names reflect each buffer's physical role: - **Shared scratch** (eval_jacobian output, reused as eval_mass_matrix's `J` input to skip a re-compute): `_jacobian_buf_flat`, `_joint_S_s_buf` (Featherstone motion subspace — shared between the two evals, hence the property-prefix-free name). - **Per-view gather config**: `_jacobian_link_offset` (fixed-base row-0 skip), `_jacobian_view_art_ids` (flattened view-to-model index map). - **`body_com_jacobian_w`**: `_jacobian_buf` (zero-copy 4-D view of `_jacobian_buf_flat`, kernel input) and `_body_com_jacobian_w_buf` (gather output, per-view). - **`body_link_jacobian_w`**: `_body_link_jacobian_w_buf` (Center-Of-Mass-to-link-origin shift kernel output, per-view). - **`mass_matrix`**: `_mass_matrix_full_buf` (model-wide `H` scratch — Composite Rigid Body Algorithm (CRBA) output), `_mass_matrix_body_I_s_buf` (Featherstone per-body spatial inertia aux, CRBA-only), `_mass_matrix_buf` (gather output, per-view). Properties are allocation-free at step time. The kernel-launch sequence runs against fixed buffer pointers, which is what makes the per-step path safe under CUDA-graph capture. ### 4.2 View-level row gather Newton's `eval_jacobian` / `eval_mass_matrix` write every articulation in the model into a single buffer (shape includes `model.articulation_count`), regardless of which `ArticulationView` invoked them. PhysX returns view-scoped data already. Two Warp kernels (`gather_jacobian_rows` 4-D, `gather_mass_matrix_rows` 3-D) gather just this view's rows into a contiguous view-sized destination so the caller-facing shape contract matches PhysX. The view-to-model index map is reused across both gathers. ### 4.3 `eval_mass_matrix` "J as input" gotcha Newton's `eval_mass_matrix(state, H, J=None, body_I_s=None, joint_S_s=None)` treats `J` as **input** when provided — it skips the internal `eval_jacobian` and uses the buffer as-is. Passing an empty pre-allocated `J` produces `H = J^T·M·J = 0` → singular → `LinAlgError` in OSC's `torch.inverse(mass_matrix)`. The wrapper explicitly populates `J` by calling `eval_jacobian` first; we reuse `_jacobian_buf_flat` (same shape) so no separate scratch is needed. ### 4.4 COM→origin shift on `body_link_jacobian_w` Newton's `eval_jacobian` writes linear-velocity rows at each link's **center of mass**. After `gather_jacobian_rows`, the `shift_jacobian_com_to_origin` Warp kernel applies `v_origin = v_com - ω × (R · body_com_pos_b)` per `(env, body, dof)` thread, writing to `_body_link_jacobian_w_buf`. The COM-referenced source buffer is reused as-is for `body_com_jacobian_w` and `mass_matrix`. ### 4.5 FK staleness `eval_jacobian` and `eval_mass_matrix` read `state.body_q` (per-body world transforms). After a manual `write_joint_position_to_sim_*` (no sim step), `state.joint_q` is updated but `state.body_q` is stale until `eval_fk` runs. The new properties match the existing `body_link_pose_w` convention — refresh FK lazily via `_ensure_fk_fresh()` (Python-guarded `SimulationManager.forward()`) before invoking the eval kernels. PhysX has its own internal refresh on the equivalent getters (verified empirically by the new manual-write tests passing on PhysX without an explicit trigger). ## 5. Action-term gating `OperationalSpaceControllerAction._compute_dynamic_quantities` previously fetched mass matrix and gravity-compensation forces unconditionally on every step. Under the new abstraction this would still call Newton's gravity-comp stub even when the user disabled gravity compensation in the controller config. The fetches are now gated to match what the controller actually consumes: - Mass matrix fetched when `inertial_dynamics_decoupling=True` **or** `nullspace_control != "none"` (the null-space torque term in `OperationalSpaceController.compute()` consumes mass matrix independently of inertial decoupling). - Gravity comp fetched only when `gravity_compensation=True`. Side benefit: skips a per-step engine call on PhysX when neither flag is set. ## 6. Known limitation: gravity compensation on Newton Newton's `ArticulationView` has no gravity-compensation primitive (only `eval_fk` / `eval_jacobian` / `eval_mass_matrix`). `gravity_compensation_forces` raises `NotImplementedError` on Newton; OSC users on Newton must set `gravity_compensation=False` until upstream lands the primitive (newton-physics/newton#2497, isaac-sim#2529, isaac-sim#2625). The strict-xfail test `test_get_gravity_compensation_forces_not_implemented_on_newton` flips to XPASS when that happens, signaling the maintainer to remove the wrapper stub and OSC guidance. ## 7. Reach-env cfg cleanup Removed the `self.sim.physics = PhysxCfg(bounce_threshold_velocity=0.2)` override from `Isaac-Reach-Franka-{IK-Abs,IK-Rel,OSC}-v0`. Tasks now inherit the parent `ReachPhysicsCfg` preset, so `presets=newton` selects `NewtonCfg` and `presets=physx` (the default) keeps the previous behavior — same `bounce_threshold_velocity=0.2` lives on `ReachPhysicsCfg.default = PhysxCfg(bounce_threshold_velocity=0.2)`. No information lost. ## 8. Test plan ### 8.1 Existing controller tests migrated - [x] `test_differential_ik.py` migrated to `robot.data.body_link_jacobian_w.torch`. Passes on PhysX (2/2). - [x] `test_operational_space.py` migrated to `robot.data.body_link_jacobian_w.torch`, `robot.data.mass_matrix.torch`, `robot.data.gravity_compensation_forces.torch`. PhysX (12/18 — the 6 failures are pre-existing `ContactSensor` env issues unrelated to this PR; affected tests fail on `omni.physics.tensors.api` import which is independent of the bridge). - [x] `test_floating_base_osc_action_term_indexing` cfg unchanged. ### 8.2 New tests in this PR **Shape contracts** — lock the public DoF / body axes: | Test | Backend | Purpose | Result | |------|---------|---------|--------| | `test_get_jacobians_shape_fixed_base` | PhysX + Newton | `body_link_jacobian_w` drops the fixed-root row → `(N, B−1, 6, J)`. | PASSES | | `test_get_jacobians_shape_floating_base` | PhysX + Newton | Floating base keeps root row + prepends 6 base cols → `(N, B, 6, J+6)`. | PASSES | | `test_get_mass_matrix_shape_and_nonsingular_fixed_base` | PhysX + Newton | `(N, J, J)` + strictly positive diagonal (catches the model-wide-padding bug that masks heterogeneous-scene mismatch as a singular matrix). | PASSES | | `test_get_mass_matrix_shape_floating_base` | Newton | `(N, J+6, J+6)` — floating-base includes the 6 free-root DoFs. | PASSES | | `test_heterogeneous_scene_per_view_shapes` | Newton | Mixed Franka+Anymal scene: each view returns its OWN asset shape, not `model.max_*`. Direct regression test for the heterogeneous-padding bug. | PASSES | **Math / physics contracts** — values, not just shapes: | Test | Backend | Purpose | Result | |------|---------|---------|--------| | `test_get_jacobians_link_origin_contract[panda \| anymal]` | PhysX | `J · q̇ == body_link_lin_vel_w` identity (sharp J reference-point check). Anymal exercise catches the latent COM/link mismatch this PR fixes. | PASSES | | `test_get_jacobians_link_origin_contract[panda \| anymal]` | Newton | Same identity, ground truth from `state.body_qd` minus the COM offset shift. | PASSES | | `test_get_mass_matrix_symmetry_pd[panda \| anymal]` | PhysX + Newton | `M(q)` is square, symmetric, positive-definite. | PASSES (4/4) | **Freshness contracts** — Forward Kinematics (FK) refresh after manual writes: | Test | Backend | Purpose | Result | |------|---------|---------|--------| | `test_jacobian_refreshes_after_manual_joint_write[panda \| anymal]` | PhysX + Newton | After `write_joint_position_to_sim_index` (no sim step), reading the Jacobian reflects the new joint state. Locks in the FK-staleness contract on the manual-write code path. | PASSES (4/4) | | `test_mass_matrix_refreshes_after_manual_joint_write[panda \| anymal]` | PhysX + Newton | Same contract for mass matrix. | PASSES (4/4) | **Gravity compensation** — accessor + Operational Space Control (OSC) integration + negative control: | Test | Backend | Purpose | Result | |------|---------|---------|--------| | `test_get_gravity_compensation_forces_static_equilibrium` | PhysX | Apply only `τ_gc` to a non-trivial Franka pose; assert it stays static. Pins the accessor in isolation, no controller masking. | PASSES | | `test_franka_osc_gravity_compensation_holds_under_gravity` | PhysX | OSC + `gravity=g(q)` under scene gravity holds the EE pose. Pins (a) `_jacobi_joint_idx + num_base_dofs` indexing, (b) `OSC.compute(gravity=...)` torque math, (c) reachability through the action-term pipeline. | PASSES | | `test_franka_osc_no_gravity_compensation_sags_under_gravity` | PhysX | Negative control — OSC **without** gravity comp DOES drift under gravity. Proves the with-comp test isn't passing because `g(q)=0`. | PASSES | | `test_get_gravity_compensation_forces_not_implemented_on_newton` | Newton | Strict-xfail pin for the upstream Newton gap. Flips to XPASS when upstream lands the primitive. | XFAIL (correct) | **End-to-end Inverse Kinematics (IK) and OSC accuracy** — production sentinels: | Test | Backend | Purpose | Result | |------|---------|---------|--------| | `test_franka_ik_tracking_accuracy` | PhysX + Newton | Damped-Least-Squares IK convergence sentinel via the new accessors. | PASSES (PhysX 0.01 mm, Newton 0.00 mm) | | `test_franka_osc_tracking_accuracy` | PhysX + Newton | OSC convergence sentinel via Jacobian + mass matrix. | PASSES (both at machine precision) | Latest CI: `isaaclab_physx` and `isaaclab_newton` both green on the most recent push. ### 8.3 Determinism and stability The accuracy sentinels are bit-for-bit deterministic on both backends at the 5 cm short-target setup: 20× consecutive runs each give the same `pos_mean` to 5 decimal places. Both tests assert on tail mean rather than tail min — the latter is the bottom of any oscillation envelope and can pass spuriously while the actual tracking error is much larger. Tight regression sentinels rather than flaky bounds. No `pytest-rerunfailures` retry decoration — a CI failure should be a real regression, not noise to retry away. ### 8.4 Smoke runs - [x] `random_agent` on `Isaac-Reach-Franka-IK-Abs-v0` under Newton: 5,205 physics substeps zero-error. - [x] `random_agent` on `Isaac-Reach-Franka-IK-Rel-v0` under Newton: 306 substeps zero-error. - [x] `random_agent` on `Isaac-Reach-Franka-OSC-v0` under Newton: 290 substeps zero-error. ### 8.5 Test-setup notes The accuracy tests need two fixes that the standalone path doesn't get for free (production envs do): - Teleport to `init_state.joint_pos` post-`sim.reset()`. Without it, the robot sits at the URDF-neutral pose where Franka's wrist axes nearly align — rank-deficient Jacobian, multi-cm DLS plateau. - Override `sim_cfg.gravity = (0, 0, 0)` in the Newton `sim` fixture (`build_simulation_context(gravity_enabled=False)` is silently ignored when an explicit `sim_cfg` is passed). The OSC test additionally zeros actuator PD gains so OSC's joint-effort output isn't opposed by `kp·(target − q)` (same way OSC is wired in production action terms). With these in place, Newton hits machine precision and PhysX hits ~10 µm. Newton's PD does have a real `g_torque/kp` gravity-sag that PhysX's TGS masks via constraint projection — surfaces only when gravity is on without gravity compensation, which is the upstream gap in § 6. ## 9. Files Touched five extensions; per-package changelog fragments under `source/<pkg>/changelog.d/jichuanh-ik-newton-compat-mvp*.rst`: - `isaaclab` (minor): four new properties on `BaseArticulationData`; `num_base_dofs` on `BaseArticulation`; controller-action gating + migration to data-layer accessors; doc updates. - `isaaclab_physx`: data-layer impls + `shift_jacobian_com_to_origin` kernel; docs the latent frame-mismatch fix. - `isaaclab_newton` (minor): data-layer impls (eval + gather + shift); model-sized scratch and view-sized output buffers migrated from articulation to data layer; gravity-comp NIE stub. - `isaaclab_ovphysx`: bridge methods removed (inherits NIE). - `isaaclab_tasks`: hardcoded `PhysxCfg` removals + direct-workflow caller migrations to data-layer accessors. --------- Signed-off-by: aravind s kumar <aravikumar@nvidia.com> Co-authored-by: aravind s kumar <aravikumar@nvidia.com> Co-authored-by: Kelly Guo <kellyg@nvidia.com>

# Description The timeout retry logic is doing more harm than good as it's causing tests to run extremely long and does not actually resolve any of the timeout issues. Reverting the change to default to 0 retries on timeouts. ## 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 - [ ] 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

Replaces the earlier Python-based parent-loop implementation (which was correct but ~3× slower than USD for local poses) with a fully GPU-side Fabric path that follows the bareya/pbarejko/camera-update prototype: * Three persistent ``PrimSelection`` instances differing only in per-attribute access mode — one each for {trans_ro, world_rw, local_rw}. * Path-based view → fabric index mapping computed once from ``selection.GetPaths()`` and stored as a Warp ``int32`` array. No custom prim attributes are written to the stage. * All transform reads and writes go through ``wp.indexedfabricarray``, so the kernels just dereference ``ifa[view_index]`` instead of taking a separate mapping argument. * Stage-level ``IFabricHierarchy`` cache and dirty-stages set so multiple ``FabricFrameView`` instances on the same stage share state. World ↔ local consistency is preserved through Warp kernels that run on the affected write paths: * ``set_local_poses`` writes ``omni:fabric:localMatrix`` directly via the compose kernel, then a second kernel recomputes child worldMatrix from ``parent_world * child_local`` so the next ``get_world_poses`` read is consistent. ``IFabricHierarchy.update_world_xforms()`` is *not* used for this — in practice it re-reads USD's authored xformOps and would overwrite the matrices we just authored. * ``set_world_poses`` mirrors the above, recomputing ``child_local = inv(parent_world) * child_world`` after the write. Two new public Warp kernels in ``isaaclab.utils.warp.fabric``: * ``decompose_indexed_fabric_transforms`` / ``compose_indexed_fabric_transforms`` — indexed-array variants of the existing decompose/compose kernels. * ``update_indexed_local_matrix_from_world`` / ``update_indexed_world_matrix_from_local`` — propagate one direction using a parent indexed fabric array. Implemented directly in storage convention (``local = world * inv(parent)``, ``world = local * parent``) — the four transposes the math-convention form would imply cancel out under ``(A·B)^T = B^T·A^T``. Benchmark (1024 prims, 50 iterations, RTX A6000): Operation USD (ms) Fabric (ms) Speedup Get World Poses 12.33 0.044 282× Set World Poses 27.98 0.117 240× Interleaved Set→Get 41.34 0.160 258× Get Local Poses 6.04 0.037 162× Set Local Poses 8.54 0.053 162× Local-pose ops went from ~3× slower than USD (in the earlier torch-based parent-loop implementation) to ~160× faster, with the new Fabric-side localMatrix authoring keeping ``test_set_world_updates_local`` passing without an xfail override. Tests: 41 passed in the Fabric backend's contract + new coverage for the Fabric-native ``set_local_poses``, ``get_scales``, and topology rebuild paths. Drops the no-longer-needed ``cd571d482`` Python-loop attempt.

Three review fixes on the indexedfabricarray refactor: * set_scales wrote the new scale into worldMatrix but never refreshed localMatrix, so a subsequent get_local_poses returned the stale scale. Call _sync_local_from_world after the world write, matching set_world_poses. * The view->fabric mapping was stored in a single shared _fabric_indices field that each accessor overwrote from its own selection's GetPaths() ordering. Selections do not guarantee a shared path ordering, so this was brittle and hard to reason about. Cache the mapping per selection (_trans_ro_fabric_indices, _world_rw_fabric_indices, _local_rw_fabric_indices) and pass it explicitly to _build_indexed_array. The three trans_ro accessors now share a _rebuild_trans_ro_arrays helper. * Update two test comments that referenced the removed _fabric_usd_sync_done attribute to point at the lazy _initialize_fabric() call instead.

The chained set_world_poses -> get_world_poses round-trip in test_fabric_rebuild_after_topology_change goes through Warp's float32 SRT compose/decompose, which accumulates a few ULP of drift. At the test's position magnitudes (~4-6), one float32 ULP is ~4.77e-7, so the prior atol of 1e-7 demanded sub-ULP agreement and was sensitive to GPU/codegen variation -- it passed locally on the A6000 but flaked in CI. 1e-5 corresponds to roughly 20 ULP at those magnitudes: tight enough to catch any real bug (a wrong index or stale read would be at least ~1e-3 off given the test setup) and consistent with the shared contract harness in frame_view_contract_utils.py, which already documents and uses ATOL = 1e-5 for compose/decompose-through-float32 checks.

The previous _static_dirty_stages set was keyed by stage_id, but _sync_world_from_local_if_dirty only recomputes worldMatrix for the *calling view's* children before clearing the flag. With two views on the same stage, view B's world-read would clear the flag set by view A's set_local_poses, leaving A's worlds silently stale. Replace the class-level set with a per-instance bool. Each view now tracks its own dirty state, which matches the actual scope of the recompute kernel and removes a mutable ClassVar. Also: - Raise a clearer error when _compute_parent_fabric_indices is asked to look up the parent of a root-level prim (rsplit produces ""), instead of bubbling up the generic "not found in selection" message. - Document on the remaining _static_hierarchy_cache that it is not thread-safe by design (Isaac Lab's loop is single-threaded; adding a lock would negate the per-stage caching benefit). - Update the module docstring to reflect the per-view dirty model and drop the stale reference to IFabricHierarchy.update_world_xforms.

Three review fixes plus the missing coverage for the transpose storage convention. * Hierarchy cache eviction: cache key is now (stage_id, fabric_id) so a recycled stage_id paired with a new Fabric attachment never returns a stale handle. Added FabricFrameView.clear_static_caches() classmethod for explicit teardown and wired it into the test fixture so cached handles do not accumulate across the suite. * PrepareForReuse no longer fires twice per sync. Both _sync_local_from_world and _sync_world_from_local_if_dirty refresh trans_sel_ro exactly once, then read _world_ifa_ro / _local_ifa_ro / _parent_world_ifa_ro directly from the fields instead of going through the accessors. * Class docstring rewritten to describe the actual PrepareForReuse policy (every accessor calls it; idempotent and cheap in the steady state). The prior wording claimed reads avoided PrepareForReuse, which has not been true since the indexedfabricarray rewrite. * New regression tests for the transpose storage convention. The standard fixture parents are translation-only, so the rotation block is identity and equal to its transpose - which means a wrong transpose convention would still pass every existing test. Two new tests place a parent rotated 90 degrees around Z and verify the world<->local round-trip: - test_set_local_then_get_world_with_rotated_parent exercises update_indexed_world_matrix_from_local - test_set_world_then_get_local_with_rotated_parent exercises update_indexed_local_matrix_from_world Confirmed locally that flipping the multiply order in either kernel makes the matching test fail. 45 tests pass on cpu and cuda:0.

FabricFrameView is referenced by fully-qualified name in the migration guide and in this PR's changelog fragment, but no RST file documented the module - so the Sphinx :class: and :meth: cross-refs were not resolvable. Add a thin automodule page mirroring the sibling pages under docs/source/api/lab_physx/ and register it in the API index toctree. This also picks up the new clear_static_caches() classmethod automatically via :members:.

The submodule was not surfaced anywhere in the Sphinx tree, so :func: cross-references to its kernels (added in the changelog fragment for this branch and used by FabricFrameView throughout) did not resolve. Add a Warp Fabric kernels subsection to isaaclab.utils.rst that automodule's the submodule, and add __all__ to fabric.py so the generated page lists only the eight public kernels - the type aliases (FabricArrayMat44d, ArrayUInt32, ...) and the re-imported `wp` / `TYPE_CHECKING` / `Any` symbols stay out of the rendered docs. The page covers both the pre-existing kernels (compose/decompose_fabric_transformation_matrix_*_warp_arrays, set_view_to_fabric_array, arange_k) and the four kernels added on this branch.

_sync_fabric_from_usd_initial had two scale-related bugs in the USD->Fabric seed path that produced silently wrong matrices whenever a parent or child had a non-unit scale. Both kernels that recompute world<->local consistency read those seeded matrices, so the error propagated. * Parent worldMatrix was composed with a hardcoded (1, 1, 1) scale. Orthonormalize() strips scale from the local-to-world transform, so we now extract the scale via Gf.Transform.GetScale() *before* orthonormalizing and pass it through to the compose kernel. * Child localMatrix was composed with the empty-array sentinel for the scale slot, leaving the kernel-side scale at the identity default. We now pass the locally-authored scale (already fetched via _usd_view.get_scales()) so the matrix carries the right scale. * Child worldMatrix is still composed from get_world_poses() position and orientation plus the child's local scale, which is wrong when a parent has non-unit world scale. Instead of fixing the seed by hand (would require per-child world-scale lookups), mark the view dirty at the end of the seed. The very next world read fires _sync_world_from_local_if_dirty, which computes child_world = parent_world * child_local on the GPU - and with both matrices now correctly scaled, the multiply produces the right world-space scale automatically. Added test_initial_seed_with_scaled_parent regression test: parent world scale (2, 1, 1), child local scale (3, 1, 1). Locally verified the test fails when either fix is reverted in isolation.

While adding a regression test for the per-view world-dirty flag, I discovered the IFabricHierarchy cache silently misses on every view because ``Stage.GetFabricId()`` returns a fresh ``FabricId`` wrapper on every call, with no value equality between wrappers for the same underlying Fabric. The cache stored (stage_id, wrapper) tuples, so two views on the same stage produced two distinct cache keys and re-fetched the hierarchy on each init. The bug was harmless in practice -- USDRT's ``get_fabric_hierarchy`` itself returns a process-wide singleton per Fabric stage, so both views happened to end up with the same handle anyway -- but the cache wasn't doing the work it was advertised to do. Fix: key the cache on ``(stage_id, fabric_id.id)`` where ``.id`` is the stable ``int`` underneath the wrapper. The new test exercises the multi-view-per-stage scenario: * two FabricFrameView instances on disjoint child prims under different parent sub-trees of one stage * writes on view A must not dirty view B * world reads on view B must not clear view A's dirty flag * both views share one cached IFabricHierarchy and the cache has exactly one entry after both inits (this assertion is what surfaced the FabricId-wrapper bug) * symmetric pass: writes on B must not affect A's post-read state Verified locally that the test fails with both the wrapper-keyed cache (cache size > 1) and with a synthetic stage-shared dirty flag (cross-view stomp). Module-level coverage of fabric_frame_view.py with this test added: 85% line / 78% branch. Remaining uncovered code is the USD-fallback delegations (Fabric disabled), defensive RuntimeError raises, and topology-rebuild branches inside the accessors. 49 tests pass on cpu and cuda:0.

… kernels Replace if/else broadcast branching with wp.where() for branchless predicated selection. wp.select was deprecated in Warp 1.7 and removed in 1.10; wp.where has the more intuitive (cond, true, false) order.

github-actions Bot added the isaac-lab label May 5, 2026

pv-nvidia changed the title ~~Pv/5381 rebased~~ Implement Fabric-aware get/set_local_poses via indexedfabricarray May 5, 2026

matthewtrepte and others added 6 commits May 5, 2026 13:13

pv-nvidia force-pushed the pv/5381-rebased branch from 7d135d0 to 71a38d2 Compare May 7, 2026 11:37

github-actions Bot added documentation Improvements or additions to documentation infrastructure labels May 7, 2026

r-schmitt and others added 19 commits May 7, 2026 11:53

[CI][Auto Version Bump] Compile changelog fragments (schedule)

99b0359

Bumped packages: - isaaclab: 4.7.0 → 4.8.0 - isaaclab_mimic: 1.2.5 → 1.2.6 - isaaclab_newton: 0.6.0 → 0.7.0 - isaaclab_ov: 0.1.4 → 0.1.5 - isaaclab_physx: 0.6.0 → 0.6.1

[Visualizers] Fix viewergl fully-black: assign PyVec3 to Newton camer…

23ababb

…a.pos (isaac-sim#5547)

kellyguo11 and others added 7 commits May 11, 2026 16:10

pv-nvidia force-pushed the pv/5381-rebased branch from bab8ca0 to 5a04061 Compare May 12, 2026 15:10

ooctipus and others added 20 commits May 12, 2026 10:28

[CI][Auto Version Bump] Compile changelog fragments (schedule)

b8fead4

Bumped packages: - isaaclab: 5.1.0 → 5.1.1 - isaaclab_newton: 0.8.0 → 0.8.1 - isaaclab_ov: 0.1.7 → 0.1.8 - isaaclab_physx: 0.6.3 → 0.6.4 - isaaclab_tasks: 1.5.37 → 1.5.38

Some cleanup

92d3445

Fixed tests

b7f5158

pv-nvidia force-pushed the pv/5381-rebased branch from 5b4f91e to bb778db Compare May 13, 2026 19:58

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Implement Fabric-aware get/set_local_poses via indexedfabricarray#2

Implement Fabric-aware get/set_local_poses via indexedfabricarray#2
pv-nvidia wants to merge 62 commits into
fix/fabric-prepare-for-reusefrom
pv/5381-rebased

pv-nvidia commented May 5, 2026 •

edited

Loading

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

18 participants

Conversation

pv-nvidia commented May 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Implementation summary

Benchmark results

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

18 participants

pv-nvidia commented May 5, 2026 •

edited

Loading