[OVPHYSX] Articulation rewrite (data class + asset class + kernels)#5459
Merged
kellyguo11 merged 85 commits intoMay 16, 2026
Merged
Conversation
Add nine RIGID_BODY_* aliases to isaaclab_ovphysx.tensor_types covering the rigid-actor root pose/velocity/acceleration, wrench application, and mass/inertia/COM properties. Each alias carries a shape/units docstring that Sphinx autoattribute can pick up. Extend _CPU_ONLY_TYPES with the five CPU-routed rigid-body variants so the existing GPU/CPU dispatch in _to_flat_f32 routes them correctly. Direct imports (no shim) intentionally couple this package to a future ovphysx wheel that exposes the matching TensorType enum values; see docs/superpowers/specs/2026-04-27-ovphysx-rigid-body-tensortypes-gap.md. Issue: isaac-sim#5316
Move kernels reused across multiple asset types from isaaclab_ovphysx.assets.articulation.kernels into a new isaaclab_ovphysx.assets.kernels module: _body_wrench_to_world, _scatter_rows_partial, _copy_first_body, _compose_root_com_pose, _projected_gravity, _compute_heading, _world_vel_to_body_lin, _world_vel_to_body_ang. Articulation-only kernels (joint-limit setup, FD joint acceleration, multi-body COM compose) stay in articulation/kernels.py. Articulation modules update their imports accordingly. No behavior change. This refactor unblocks the upcoming RigidObject implementation, which needs the same kernels for frame conversions and wrench packing. Issue: isaac-sim#5316
Generalize the mock binding factory to produce a rigid-object-shaped binding set (RIGID_BODY_* keys only, num_joints=0, num_bodies=1, no tendons) when called with asset_kind='rigid_object'. Default behavior is unchanged: existing articulation callers do not need updates. Make set_random_data tolerant of the smaller binding set so it works for both asset kinds. Issue: isaac-sim#5316
Add the rigid_object sub-package and the RigidObjectData class skeleton with constructor, count properties, update/invalidate hooks, and _process_cfg that fills _default_root_pose / _default_root_velocity from cfg.init_state. Add the backend-specific test file with a hasattr-based wheel gate (importorskip-then-attr on the module would AttributeError rather than skip when RIGID_BODY_* enums are absent on the wheel) and a basic-counts smoke test. Issue: isaac-sim#5316
Address review blockers on commit 65084f7: 1. _process_cfg now mirrors the articulation pattern (wp.zeros to pre-allocate, then wp.copy from wp.from_numpy with the typed dtype directly — matching articulation._process_cfg verbatim), avoiding the use-after-free that the previous reinterpret-cast-from-local idiom introduced when the float32 source went out of scope. 2. is_primed is now a guarded @Property + setter that enforces the one-way gate (False->True allowed, True->True idempotent, True->False raises ValueError), matching every other *Data class. 3. Drop unused forward-reference imports from test/assets/test_rigid_object.py so ruff/F401 passes; subsequent tasks will re-add them when the symbols are actually used. Issue: isaac-sim#5316
Replace the abstract-property stubs for root_link_pose_w, root_link_vel_w, root_com_pose_w, root_com_vel_w, and the per-axis sliced views (root_link_pos_w, root_link_quat_w, root_lin_vel_w, root_ang_vel_w, plus their root_com_* counterparts) with concrete implementations that lazy-read from RIGID_BODY_ROOT_POSE / RIGID_BODY_ROOT_VELOCITY through TensorBindings, cache for the rest of the sim step, and expose slices as zero-copy Warp views over the canonical pose/velocity buffers. Mirrors the articulation_data lazy-read + ProxyArray + sliced-view idioms with num_bodies=1 (root pose/velocity are 1-D over instances, with no body axis). Issue: isaac-sim#5316
The per-property TimestampedBuffer.timestamp fields are the freshness gate consulted by every lazy-read property. _invalidate_caches was previously clearing only the legacy _timestamps dict, leaving the buffers with their last-read timestamp; a property accessed within the same sim step (e.g. immediately after RigidObject.reset and before update(dt) advances _sim_time) would serve pre-reset data. Reset every allocated buffer's timestamp to -1.0 in _invalidate_caches so the next property access always re-reads from the binding regardless of where _sim_time stands. Add a regression test that mutates the binding in place + calls _invalidate_caches without advancing _sim_time and asserts the next read reflects the new value. Issue: isaac-sim#5316
Replace the abstract-property stubs for the body-state singleton-dim
views (body_link_pose_w, body_com_pose_w, body_*_vel_w, body_*_pos_w,
body_*_quat_w, body_*_lin_vel_w, body_*_ang_vel_w), the body
acceleration (body_link_acc_w, body_com_acc_w, plus their _lin_*/
_ang_* slices) gated on the RIGID_BODY_ACCELERATION binding, and the
body-frame derived properties (projected_gravity_b, heading_w,
root_link_lin_vel_b, root_link_ang_vel_b, root_com_lin_vel_b,
root_com_ang_vel_b).
Body-state views are zero-copy reshapes of the (N,) root buffers into
(N, 1, k) — no compute kernel needed when num_bodies=1. Body
acceleration raises NotImplementedError with a pointer to the gap
spec if the wheel lacks RIGID_BODY_ACCELERATION. Derived properties
launch the relocated _projected_gravity / _compute_heading /
_world_vel_to_body_{lin,ang} kernels from
isaaclab_ovphysx.assets.kernels.
Extend _invalidate_caches with the new TimestampedBuffer instances so
they participate in coarse cache invalidation.
Issue: isaac-sim#5316
The IsaacLab projected_gravity_b convention (per BaseRigidObjectData docstring "Projection of the gravity direction on base frame", and matching ArticulationData which normalizes gravity_np / gravity_mag before storing GRAVITY_VEC_W) is the unit direction, not the signed-magnitude. The Task 6 test assertion expected -9.81 (signed magnitude); the kernel correctly produces -1.0 (unit z-component of the gravity direction). Update the assertion and the inline comment so the test reflects the documented contract. Issue: isaac-sim#5316
Replace the abstract-property stubs for body_mass, body_inertia, and body_com_pose_b with concrete CPU-side lazy-read implementations backed by RIGID_BODY_MASS / RIGID_BODY_INERTIA / RIGID_BODY_COM_POSE bindings. Also implement body_com_pos_b and body_com_quat_b as zero-copy slice views of body_com_pose_b's transformf buffer. Properties read once on first access, cache as semi-static, and invalidate via the _invalidate_caches reset loop (driven by RigidObject mass/COM/inertia setters). Mirrors the articulation_data pattern adapted for num_bodies = 1. Issue: isaac-sim#5316
Add RigidObject class with __init__, _initialize_impl, _get_binding, and count/data accessor properties. Eagerly creates GPU bindings for RIGID_BODY_ROOT_POSE / RIGID_BODY_ROOT_VELOCITY / RIGID_BODY_WRENCH so binding-creation failures surface at init time with a clear message pointing at the gap spec. _create_buffers and _process_cfg are placeholder no-ops; Task 9 replaces them. Write paths, reset, update, find_bodies, and the deprecated state writers come in subsequent tasks (10-13). Abstract methods that must be satisfied to instantiate the class are stubbed with NotImplementedError pending those tasks. Issue: isaac-sim#5316
Renames per Marco's feedback: RIGID_BODY_ROOT_POSE -> RIGID_BODY_POSE and RIGID_BODY_ROOT_VELOCITY -> RIGID_BODY_VELOCITY throughout. "Root" is articulation vocabulary; a standalone rigid body IS the body. Shape correction: RIGID_BODY_MASS and RIGID_BODY_INV_MASS ship as (N,) not (N, 1). MockOvPhysxBindingSet allocates (N,) for both; rigid_object_data.py's body_mass property consumes (N,) and exposes (N, 1) via zero-copy reshape to satisfy the BaseRigidObjectData contract. Soften _initialize_impl error: removes the prescriptive "NOT under an articulation root" language since pattern- resolution gating is a future wheel-side selection policy. Pre-existing ruff E501 in write_root_link_state_to_sim docstring fixed as collateral.
Allocate _ALL_INDICES, _ALL_BODY_INDICES, their Warp views, the single-body (N, 1, 9) _wrench_buf staging buffer, and the instantaneous/permanent wrench composers. _process_cfg delegates to RigidObjectData._process_cfg. Issue: isaac-sim#5316
Add the twelve root-state writers (pose+velocity, actor+link+com, index+mask variants) on RigidObject, plus the shared _to_flat_f32 and _write_root_state helpers ported from articulation. Frame-conversion variants launch the relocated assets/kernels.py kernels before the binding write. Add the three deprecated compound state writers that emit DeprecationWarning and delegate to the split pose+velocity writers. Add _compose_root_link_pose_from_com kernel to assets/kernels.py to support COM->link pose inversion on the write path: link_pose = com_pose_w * inverse(com_pose_b) Issue: isaac-sim#5316
Add set_masses_{index,mask}, set_coms_{index,mask},
set_inertias_{index,mask}. Each writes through the matching
CPU-routed RIGID_BODY_* binding via _write_root_state, then
invalidates the corresponding RigidObjectData cache via
_invalidate_caches.
body_ids / body_mask parameters are accepted for parity with the
BaseRigidObject contract but unused (num_bodies = 1).
Extend _write_root_state to handle 1-D bindings (RIGID_BODY_MASS)
by detecting them and bypassing the 2-D scatter kernel path.
Issue: isaac-sim#5316
Compose instantaneous + permanent wrenches, rotate body-frame force/torque to world frame via _body_wrench_to_world (dim=(N, 1)), reshape the (N, 1, 9) staging buffer to (N, 9) zero-copy, write to RIGID_BODY_WRENCH, reset the instantaneous composer. Issue: isaac-sim#5316
Replace stubs for reset, update, and find_bodies. reset writes the default pose/velocity to the specified envs via zero-copy flat float32 views of the typed wp.transformf/wp.spatial_vectorf defaults, resets both wrench composers, and invalidates the data caches. update delegates to RigidObjectData.update. find_bodies handles the None (all bodies) fast path and delegates regex matching to resolve_matching_names for non-None inputs. The deprecated compound state writers were already implemented in Task 10 alongside the split-form writers and are not touched here. Issue: isaac-sim#5316
Add the rigid_object/__init__.pyi stub mirroring the articulation sibling, and extend isaaclab_ovphysx.assets/__init__.pyi to include RigidObject and RigidObjectData. Public imports now resolve via ``from isaaclab_ovphysx.assets import RigidObject, RigidObjectData``. Issue: isaac-sim#5316
Add the import-guarded BACKENDS.append('ovphysx') block, the
create_ovphysx_rigid_object factory, and the dispatch case so the
existing parametrized interface tests automatically cover the new
backend. Mirrors the OVPhysX articulation parametrization in
test_articulation_iface.py.
Issue: isaac-sim#5316
Mirror the Cartpole/Ant pattern by adding ovphysx variants to ObjectCfg (RigidObjectCfg using the same DexCube spawn as the physx variant) and to PhysicsCfg (OvPhysxCfg()). Default backend remains physx; existing PhysX/Newton paths are unchanged. This wires Isaac-Repose-Cube-Allegro-Direct-v0 for OVPhysX validation via ./scripts/run_ovphysx.sh source/isaaclab_tasks/isaaclab_tasks/ direct/allegro_hand/allegro_hand_env.py --num_envs 4 --headless once the wheel ships. Issue: isaac-sim#5316
Add the 0.2.0 changelog entry on isaaclab_ovphysx covering the new RigidObject/RigidObjectData classes, the RIGID_BODY_* TensorType aliases (six already-shipping + three pending wheel update), the mock-binding asset_kind extension, and the assets/kernels.py kernel relocation. Bump the matching extension.toml version. Add a patch-bump changelog entry on isaaclab_tasks for the Allegro env preset addition. Issue: isaac-sim#5316
The ovphysx wheel currently exposes 6 of the 9 RIGID_BODY_* TensorType enums (POSE, VELOCITY, WRENCH, MASS, COM_POSE, INERTIA). The remaining three (ACCELERATION, INV_MASS, INV_INERTIA) are pending an upcoming wheel update from @marcodiiga. Make the IsaacLab side wheel-update-agnostic: * Guard tensor_types.py imports of the three not-yet-shipping aliases with try/except AttributeError so isaaclab_ovphysx.tensor_types imports cleanly on today's wheel. _CPU_ONLY_TYPES filters to only the names that exist via _RIGID_BODY_OPTIONAL_CPU. * MockOvPhysxBindingSet skips the optional bindings when their alias is not defined. * RigidObjectData.body_*_acc_w now finite-differences from body_com_vel_w, mirroring Newton's pattern (kernel derive_body_acceleration_from_body_com_velocities ported into isaaclab_ovphysx.assets.kernels). Removes the NotImplementedError-on-missing-binding fallback. * update(dt) stores _last_dt and eagerly triggers body_com_acc_w each step so FD captures every transition. The forward-compat aliases stay declared (Marco will land them); when they ship, the existing TensorBinding read path will work without further IsaacLab changes. Issue: isaac-sim#5316
WrenchComposer.__init__ calls hasattr(asset.data, "body_com_pos_w"), which triggers the property chain body_com_pos_w → body_com_pose_w → root_com_pose_w, reading the RIGID_BODY_COM_POSE binding and setting _body_com_pose_b_buf.timestamp = _sim_time = 0.0. Any subsequent mutation of the binding (e.g. set_coms_index, or a test that sets the binding directly) is then invisible to _com_pose_to_link_pose because the freshness gate ``buf.timestamp >= _sim_time`` treats 0.0 ≥ 0.0 as "already fresh" and skips the read — returning stale buffer contents to the frame-conversion kernel and producing an off-by-translation result. Force a fresh read in _com_pose_to_link_pose by resetting the buffer timestamp to -1.0 immediately before calling _read_transform_binding. The frame conversion always needs the current binding value at write time; the lazy-cache is the wrong policy here. Caught by test_write_root_com_pose_to_sim_index_invokes_frame_conversion. Issue: isaac-sim#5316
When running via ./scripts/run_ovphysx.sh, the test file's unconditional AppLauncher call segfaults during pytest collection because the script's thin Kit shell (libcarb preload only, no full Kit boot) cannot host a real AppLauncher. Mirror the _kitless heuristic from test_articulation_iface so the rigid-object iface tests skip AppLauncher and substitute MagicMock isaacsim core modules in the same scenarios. The original _kitless heuristic (LD_PRELOAD == "" and EXP_PATH not set) was also incorrect for this environment: run_ovphysx.sh sets LD_PRELOAD to the ovphysx libcarb.so path, not an empty string. Fix the heuristic in both test files to check for "ovphysx" in LD_PRELOAD as the primary signal, with the bare-Python fallback retained as a secondary guard. Also extend the kitless sys.modules stub list to cover omni.physics.tensors and related Kit modules that physx_manager.py imports at module scope, which would otherwise cause a ModuleNotFoundError during collection. This unblocks running the OVPhysX-parametrized parts of the file via run_ovphysx.sh. PhysX/Newton/Mock paths are unaffected. Issue: isaac-sim#5316
Three related bugs were present in the OVPhysX RigidObject body-property write path, all contributing to the 120 test failures. First, _write_root_state's full-write path (no env_ids, no mask) had no row-count validation for 1-D bindings such as RIGID_BODY_MASS. Passing a tensor with more rows than num_instances silently reached the mock's numpy reshape and raised ValueError, but the test infrastructure expected AssertionError or RuntimeError. An explicit row-count guard now raises RuntimeError on the full-write path before any binding call. Second, the index/mask sub-write path for 1-D bindings passed the source array to binding.write() as a 2-D (K, 1) buffer (the raw shape produced by _to_flat_f32 when the caller supplies (K, 1) torch data). For the mask path this caused NumPy boolean-index assignment to fail with TypeError because it cannot scatter a 2-D array into a 1-D binding buffer. The 1-D source is now normalised to shape (K,) via a zero-copy warp array view before any write. Third, write_root_com_pose_to_sim_index and write_root_com_pose_to_sim_mask silently truncated oversized inputs inside _com_pose_to_link_pose, which hardcodes shape=(N,) for the intermediate warp array view regardless of the input size. This masked shape errors on full writes. Explicit row-count guards are now applied at the public API entry points for these two methods. Additionally, default_root_pose and default_root_vel in RigidObjectData were NotImplementedError stubs. They are now implemented to return ProxyArray wrappers over the _default_root_pose/_default_root_velocity buffers that are already populated during _process_cfg. Caught by the cross-backend TestRigidObjectWritersBody tests against the OVPhysX backend. After the fix all 372 ovphysx-parametrized cases pass. Issue: isaac-sim#5316
The mock-based test file is removed in favor of a copy of PhysX's test_rigid_object.py adapted to the kitless OVPhysX architecture: - Drop AppLauncher; mock the isaacsim and omni.* modules instead so the file imports under run_ovphysx.sh without launching Kit. - Build the test scene via MockOvPhysxBindingSet, bypassing OvPhysxManager entirely (no Kit stage export needed). - Drive sim steps via direct binding manipulation; no build_simulation_context. - Programmatically construct rigid-object shells instead of pulling DexCube USD from Nucleus. Tests that exercise OVPhysX features not yet wired (OvPhysxManager step loop, contact materials, kitless stage entry point) are explicitly xfail-marked with inline reasons. Result: 67 passed, 73 xfailed, 0 failed. See docs/superpowers/specs/2026-04-28-ovphysx-rigid-object-test-gaps.md (worktree-only, gitignored) for the consolidated gap list for Marco.
OvPhysxManager IS drivable without AppLauncher: _warmup_and_load only needs PhysicsManager._sim.stage + a couple of cfg fields, which a thin SimpleNamespace fake satisfies. Use this to convert the warmup and stage-load xfails into real-backend tests against the live ovphysx.PhysX instance. Adds _make_kitless_sim_context() helper (builds in-memory USD stage with RigidBodyAPI + CollisionAPI cube + PhysicsScene, wraps in SimpleNamespace exposing: stage, cfg.physics, cfg.device, cfg.physics_prim_path, cfg.enable_scene_query_support, cfg.dt) and a module-scoped kitless_manager_cpu fixture that drives initialize() + reset() + close(). Converts test_warmup_attach_stage_not_called_for_cpu (1 xfail) to three passing real-backend tests: - test_warmup_and_load_cpu: lifecycle assertions - test_warmup_gpu_not_called_for_cpu: CPU path skips warmup_gpu - test_stage_load_cpu: stage export + usd_handle type check Adds test_warmup_and_load_gpu as xfail pending a GPU CI runner. Result: 70 passed, 73 xfailed (was 67 passed, 73 xfailed). Update the test-gaps doc to reflect the closed gap (no wheel change required for this category). Issue: isaac-sim#5316
Drop the kitless mocks, the SimpleNamespace sim-context fake, and the MockOvPhysxBindingSet shell-injection helpers. The standard SimulationContext + UsdFileCfg(ISAAC_NUCLEUS_DIR/...) pattern works under ./scripts/run_ovphysx.sh without AppLauncher — omni.client resolves Nucleus URLs from Kit's Python directly, and SimulationContext runs kitless via has_kit() returning False. Tests now exercise real RigidObject + RigidObjectData + OvPhysxManager against live ovphysx.PhysX bindings, using the same Nucleus assets the Cartpole/Newton tests use. Material-properties tests stay xfailed pending a wheel-side RIGID_BODY_MATERIAL TensorType. GPU tests now pass (NVIDIA RTX 5000 Ada verified). Production bug surfaced: RigidObject._initialize_impl uses hasattr() on TensorBinding.body_names which propagates RuntimeError (not AttributeError), blocking all RigidObject lifecycle tests against the real backend. Fix: wrap in try/except (AttributeError, RuntimeError). Tracking: issue isaac-sim#5316. Issue: isaac-sim#5316
The previous ``hasattr(root_pose, "body_names")`` gate only catches AttributeError, but the real ovphysx TensorBinding raises TypeError on the body_names property for non-articulation tensor types such as RIGID_BODY_POSE: "Articulation metadata … is not available for tensor type 'RIGID_BODY_POSE'." Replace with try/except that catches both AttributeError and TypeError; fall back to ["base_link"]. Also fix self._device derivation: ``hasattr(self._ovphysx, "device")`` always returns False for the real PhysX object (no .device property), so the device silently fell back to "cuda:0" even when the simulation runs on CPU, causing a device mismatch in TensorBinding.read(). Use OvPhysxManager.get_device() which mirrors SimulationContext.cfg.device. Un-xfail 68 of the 70 tests tagged _INIT_IMPL_BUG in test_rigid_object.py — they now run cleanly against the live ovphysx CPU backend (59 passed). The two remaining xfails use a tightened reason (_FORCE_BALANCE_GAP): test_external_force_on_single_body drifts ~0.57 m instead of < 0.1 m, a physics-accuracy gap under investigation. Issue: isaac-sim#5316
Rewrites test_external_force_on_single_body to mirror Newton's reference implementation: 5 outer iterations with a full pose/velocity reset between each, 5 inner sim steps per iteration, force applied to every 2nd cube (indices 0::2), and alternating global/local frame each outer iteration. The old test used a single 20-step loop on env_0 only, with no resets and no is_global argument — causing error accumulation and the ~0.57 m drift. Because RigidObjectData._bindings has no RIGID_BODY_MASS entry at init time, body_mass.torch returns zeros; the USD-stage MassAPI value is read instead. The per-block drift is ~6 mm vs ~35 mm free-fall, well within the atol=1e-2 guard, so the xfail decorator is removed.
…ysx_articulation # Conflicts: # source/isaaclab_ovphysx/isaaclab_ovphysx/assets/articulation/articulation.py # source/isaaclab_ovphysx/isaaclab_ovphysx/assets/articulation/articulation_data.py # source/isaaclab_ovphysx/isaaclab_ovphysx/assets/articulation/kernels.py # source/isaaclab_ovphysx/isaaclab_ovphysx/assets/kernels.py # source/isaaclab_ovphysx/isaaclab_ovphysx/tensor_types.py
Adopt the RigidObjectData / PhysX pattern: derive instance / body / joint / tendon counts from the binding metadata (``next(iter(bindings.values()))``), and assign name lists as class-level attributes filled in by ``Articulation._initialize_impl`` after construction. The constructor signature collapses from twelve arguments to ``(bindings, device)``. Drop the ``binding_getter`` callable. Bindings the data container reads (LINK_POSE, LINK_VELOCITY, LINK_ACCELERATION, LINK_INCOMING_JOINT_FORCE, ROOT_VELOCITY, and the fixed / spatial tendon set when counts > 0) are eagerly created in ``_initialize_impl`` instead of looked up via a callback, so ``ArticulationData._get_binding`` reduces to a dict lookup. Guard the forward-kinematics call in ``body_link_pose_w`` against a missing ``OvPhysxManager`` instance, so the mocked cross-backend iface tests no longer trip ``WrenchComposer``'s ``hasattr`` probe. Drop ``test_articulation_data.py`` (covered by real-backend tests) and the two ``_data`` tendon-name assertions in ``test_articulation_helpers.py`` (propagation now lives in ``_initialize_impl``, not ``_process_tendons``). Articulation tests: 101 real-backend + 2 helpers + 1080 iface = 1183 passed.
The isaaclab_ov CI job's glob collects all ``test/`` files under
``source/isaaclab_ov*``, including the isaaclab_ovphysx tests. The
sibling ovphysx test files already guard their isaaclab_ovphysx imports
with ``pytest.importorskip("ovphysx.types", reason="ovphysx wheel not
installed")``; only ``test_articulation.py`` went straight to top-level
``from isaaclab_ovphysx.assets import Articulation``, which raised
``ModuleNotFoundError`` at collection time and failed the entire
isaaclab_ov job in the CI image (where the ovphysx wheel is not
installed).
Add the same ``importorskip`` guard so the file is skipped cleanly in
that environment, matching the established pattern from
test_articulation_helpers.py and the rigid-object fix in isaac-sim#5426.
Also add a ``.skip`` changelog fragment for the isaaclab core package
covering the iface test factory tweak in the prior commit.
c6ea8c7 to
3430279
Compare
The recent OVPhysX preset hookup for the Allegro Repose direct task adds
``from isaaclab_ovphysx.physics import OvPhysxCfg`` at module top in
``source/isaaclab_tasks/.../allegro_hand/allegro_hand_env_cfg.py``.
When sphinx walks ``isaaclab_mimic.datagen`` for autodoc, the chain
``generation.py`` → ``isaaclab_tasks.utils.parse_cfg`` →
``isaaclab_tasks.__init__.import_packages`` recursively imports every
task package's ``__init__.py``. ``isaaclab_ovphysx/tensor_types.py``
does ``from ovphysx.types import TensorType`` at module load; the
``ovphysx`` wheel is not in ``docs/requirements.txt``, so the import
raises ``ModuleNotFoundError`` and sphinx reports the failure at the
outermost autodoc'd module:
WARNING: Failed to import isaaclab_mimic.datagen.
Possible hints:
* AttributeError: module 'isaaclab_mimic' has no attribute 'datagen'
* TypeError: unsupported operand type(s) for *: 'float' and 'pi'
(the ``float * pi`` hint is the assemble_trocar ``np.pi`` mock issue
surfacing as a sphinx fallback; not the primary cause.)
Add ``ovphysx`` to ``autodoc_mock_imports`` so sphinx mocks the wheel
during doc build, mirroring how ``omni`` / ``carb`` / ``isaacsim`` are
handled. No source-side change needed.
AntoineRichard
added a commit
to AntoineRichard/IsaacLab
that referenced
this pull request
May 15, 2026
Verification agents flagged five issues against the previous two commits and one issue-isaac-sim#876 gap that the first pass missed. 1. Newton using-kamino.rst literalinclude path was one level short (../../../../../ → ../../../../../../). The previous depth resolved to a non-existent /docs/source/isaaclab_tasks/... and would have broken the sphinx build. 2. PhysX supported-features.rst listed Ray Caster, Visuo-tactile, and Camera as PhysX-specific sensors. Ray Caster and Camera are implemented in isaaclab core (backend-agnostic); Visuo-tactile lives in isaaclab_contrib. Reframe the section to separate PhysX-implemented sensors from backend-agnostic ones. Drop the unverifiable "path-traced" qualifier on the RTX renderer claim. 3. OvPhysX stub referenced only PR isaac-sim#5426 and PR isaac-sim#5459. The actual in-flight set spans six PRs: isaac-sim#5426 (merged), isaac-sim#5459, isaac-sim#5422, isaac-sim#5421, isaac-sim#5570, isaac-sim#5589. List them all with merge state, and reword "primary covered surfaces" to reflect that most are still open PRs. 4. backends/index.rst feature matrix said OvPhysX sensor coverage was "Partial" — actually only RigidObject is merged. Replace the matrix rows with concrete "In-flight (PR #...)" / "Not yet" cells. 5. Issue isaac-sim#876 asked to "review the limitations list and update it." The previous pass only reworded the intro. Refresh the task list against develop's actual newton_mjwarp coverage, add Shadow Hand / Shadow Hand Over / cabinet / dexsuite / rough-terrain locomotion, and replace the rigid bullet list with a discovery recipe so the list stops bit-rotting.
7 tasks
Merged
7 tasks
AntoineRichard
added a commit
that referenced
this pull request
May 18, 2026
# Description Adds `OvPhysxSceneDataProvider`, the OVPhysX-backend implementation of `BaseSceneDataProvider`. Enables Newton-based visualizers (Rerun, Viser, native Newton viewport) to render OVPhysX simulations. Also fixes the `SceneDataProvider` factory dispatch (and adds a regression test) so the substring check `"physx" in "ovphysxmanager"` no longer routes ovphysx to PhysX. Fixes #5327 > [!IMPORTANT] > **Stacked on #5459** (`[OVPHYSX] Articulation rewrite`). The base of this PR is `develop`, so the diff includes every commit from #5459 — review only the 16 SDP-specific commits on top (`git log antoiner/feat/ovphysx_articulation..antoiner/feat/ovphysx_scene_data_provider`). Once #5459 merges, this PR will rebase cleanly. ## Architectural notes Mirrors `PhysxSceneDataProvider` end-to-end: build a Newton model from the scene's `ClonePlan` at init (gated on `SceneDataRequirement.requires_newton_model`), then on every `update()` read body poses through ovphysx `TensorBinding`s and write them into the Newton state's `body_q` via a single Warp kernel. The interesting OVPhysX-specific surface: - **One-pattern-per-binding**: the ovphysx wheel's `PhysX.create_tensor_binding` accepts a single glob-style pattern per binding (not a list, unlike PhysX's `RigidBodyView`). We bucket Newton body paths by their env-wildcard form (`/World/envs/env_*/Robot/cart`, `/World/envs/env_*/Robot/pole`, ...), one pose+velocity binding per distinct relative path. Cartpole produces 2 bindings; Allegro hand ~17 — each covering all envs. - **`RIGID_BODY_POSE` covers everything**: confirmed via standalone probe + wheel docs that the matcher accepts any prim with `UsdPhysics.RigidBodyAPI`, including articulation links. No separate `LINK_POSE` plumbing is needed. Paths flow through a `RigidBodyAPI` filter (mirroring `PhysxSceneDataProvider._setup_rigid_body_view` line ~281) so joints and articulation-root xforms are excluded from binding patterns. - **Wheel-0.4 `binding.read(dst)` API**: pre-allocated warp destination buffers, so per-step reads are allocation-free. - **View-order reorder**: each binding's `prim_paths` is matched against the Newton `body_label` ordering to build a per-binding reorder tensor with `-1` sentinels for rows owned by other bindings. The pose merge respects partial coverage across bindings, with `FrameView` fallback for anything that lacks `RigidBodyAPI` (cameras, decorative xforms). - **Factory fix**: `SceneDataProvider._get_backend` now checks `"ovphysx"` explicitly before `"physx"` so the substring overlap doesn't route the wrong backend. ## Files changed (16 commits since `antoiner/feat/ovphysx_articulation`) - `source/isaaclab/isaaclab/physics/scene_data_provider.py` — factory dispatch fix (+9/-1). - `source/isaaclab/test/sim/test_scene_data_provider_factory.py` — new parametrized regression test (44 lines). - `source/isaaclab_ovphysx/isaaclab_ovphysx/scene_data_providers/__init__.py`, `__init__.pyi` — package scaffolding. - `source/isaaclab_ovphysx/isaaclab_ovphysx/scene_data_providers/ovphysx_scene_data_provider.py` — the provider (~760 lines). - `source/isaaclab_ovphysx/test/scene_data_providers/test_ovphysx_scene_data_provider.py` — 18 stub-based unit tests covering factory dispatch, metadata, env discovery, Newton-model build, binding setup, pose-merge orchestration, transform/velocity getters, view-order reorder, camera-transform stage walk. - `docs/source/api/index.rst` + `docs/source/api/lab_ovphysx/isaaclab_ovphysx.scene_data_providers.rst` — first `isaaclab_ovphysx` section in the API reference. - `source/isaaclab/changelog.d/antoiner-feat-ovphysx-scene-data-provider.rst` — patch fragment for the factory fix. - `source/isaaclab_ovphysx/changelog.d/antoiner-feat-ovphysx-scene-data-provider.minor.rst` — minor fragment for the new provider. ## Type of change - New feature (non-breaking change which adds functionality). - Bug fix (factory dispatch). ## Validation 1. **Unit tests** — `./isaaclab.sh -p -m pytest source/isaaclab/test/sim/test_scene_data_provider_factory.py source/isaaclab_ovphysx/test/scene_data_providers/` → 23 passed. 2. **End-to-end** — `./isaaclab.sh -p scripts/reinforcement_learning/rsl_rl/train.py --task=Isaac-Cartpole-Direct-v0 --visualizer newton --num_envs 4096 presets=ovphysx` reaches the simulation loop; visualizer renders the cartpole scene. 3. **Pre-commit** — `./isaaclab.sh -f` clean. 4. **Pattern probe** — standalone reproduction at `/tmp/probe_rigid_body_pose_on_articulation.py` confirmed `RIGID_BODY_POSE` accepts articulation-link patterns. Reproducible against the wheel's bundled minimal articulation USD. ## Known follow-ups (not in this PR) - Extract `_build_newton_model_from_clone_plan` into a shared helper used by both PhysX and OVPhysX providers (currently a verbatim copy). - `FrameView` factory could grow an explicit `"ovphysx"` registration entry (today's dispatch falls through to the `"physx"` branch, which works because `FabricFrameView` reads from the shared USD stage). - Pattern length cap: if a scene's distinct-body-path count exceeds the wheel's per-pattern matcher limit (unknown), chunk into multiple bindings indexed by buffer-row offset. Hasn't bitten yet. - A future `test_ovphysx_scene_data_provider_visualizer_contract.py` mirroring `test_physx_scene_data_provider_visualizer_contract.py`. ## 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 feature works - [x] I have added a changelog fragment under `source/<pkg>/changelog.d/` for every touched package - [x] I have added my name to the `CONTRIBUTORS.md` or my name already exists there
AntoineRichard
added a commit
to AntoineRichard/IsaacLab
that referenced
this pull request
May 18, 2026
Drop AppLauncher and the PhysX-style setup_simulation fixture in favour of the kitless _ovphysx_sim_context helper (matches test_rigid_object.py shipped in isaac-sim#5459) and the autouse device-lock fixture for ovphysx<=0.3.7. Also drop the disable_contact_processing parametrize axis: toggling the global Carbonite '/physics/disableContactProcessing' flag requires the settings manager which is not available in kitless mode. test_no_contact_reporting now exercises the same semantic via a no-filter cfg instead. The three v2-deferred tests (track_friction_forces / track_contact_points) keep their pytest.mark.skip but their bodies are fully kitless so they can be un-skipped once the ovphysx wheel ships the missing per-sensor read APIs (see docs/superpowers/specs/2026-04-27-ovphysx-contact-api-gaps.md). Run via: ./scripts/run_ovphysx.sh -m pytest source/isaaclab_ovphysx/test/sensors/test_contact_sensor.py -v
matthewtrepte
pushed a commit
to matthewtrepte/IsaacLab
that referenced
this pull request
May 18, 2026
…saac-sim#5459) # Description Drastic rewrite of OVPhysX `Articulation` and `ArticulationData` so they follow the same shape as the post-refactor OVPhysX `RigidObject` from isaac-sim#5426, with the API surface mirroring `Newton Articulation` and behavior parity with `PhysX Articulation`. Single-PR atomic rewrite, clean break (no deprecation aliases for OVPhysX-introduced renames; framework-inherited deprecated shims kept). The OVPhysX articulation diverged significantly from the rest of the framework conventions. This PR brings it back in line: same docstring template, same section ordering, same naming, same internal patterns, same lifecycle. > [!IMPORTANT] > **Stacked on isaac-sim#5426** (`[OVPHYSX] RigidObject + RigidObjectData asset`). Review only the 16 articulation-specific commits at the tip of this branch — every commit before that lands via isaac-sim#5426. Once isaac-sim#5426 merges to `develop`, this PR will rebase cleanly onto `develop`. Fixes # (none — internal refactor; no associated issue) ## Architectural changes **OVPhysX RigidObject is the design template.** It has navigated the hybrid OVPhysX surface — Newton-style mask+index dual API + PhysX-style CPU-only bindings via pinned-host staging à la isaac-sim#5329 + pull-to-refresh `binding.read(target)`: - Eager `TimestampedBufferWarp` allocation in `_create_buffers` (single source of truth — no `_invalidate_caches` / `_ensure_*_buffers` machinery). - Pinned-host CPU staging buffers for every CPU-only binding (mass, COM, inertia, all DOF properties). - `_binding_read` / `_binding_write` / `_stage_to_pinned_cpu` helpers route CPU-only types through pinned-host memory. - Every public property returns a `ProxyArray` (warp + torch dual view); raw `wp.array` for one-shot config buffers. - Counts and names (`num_instances`, `num_bodies`, `num_joints`, `body_names`, `joint_names`, ...) demoted from `@property` to plain instance attributes. - Dual mask+index API on every writer/setter (`*_index` accepts partial data; `*_mask` accepts full data with a `wp.bool` mask). - All `write_*` / `set_*` parameters are kwarg-only after `*,`. No positional. **No `full_data` flag anywhere.** - The deprecated `_write_body_state` plumbing layer is removed; deprecated state-writer shims (`write_root_state_to_sim`, etc.) call the public `write_*_to_sim_index` methods directly, mirroring RigidObject. **Articulation-specific surface** mirrors Newton 1-to-1: joint-state writers, joint-property writers (CPU-only), body-property setters (multi-body shape), joint-command target setters, external-wrench setters via `WrenchComposer`, fixed/spatial tendon setters, deprecated state-writer shims, full actuator pipeline (`compute`, `_apply_actuator_model`, `_process_actuators_cfg`). ## Files changed - `source/isaaclab_ovphysx/isaaclab_ovphysx/assets/articulation/articulation.py` — full rewrite (~3863 lines, matches Newton). - `source/isaaclab_ovphysx/isaaclab_ovphysx/assets/articulation/articulation_data.py` — full rewrite (~2504 lines). - `source/isaaclab_ovphysx/isaaclab_ovphysx/assets/kernels.py` — gained 6 articulation kernels migrated from the stop-gap `kernels_old.py` (now deleted): `_compose_root_com_pose`, `_compute_heading`, `_copy_first_body`, `_projected_gravity`, `_world_vel_to_body_ang`, `_world_vel_to_body_lin`. Plus 2 new joint-property kernels (`write_joint_position_limit_to_buffer_index/mask` for trailing-dim-2 limits, `write_joint_friction_to_buffer_index/mask` for the broadcast-coefficient pattern). - `source/isaaclab_ovphysx/isaaclab_ovphysx/assets/kernels_old.py` — deleted. - `source/isaaclab_ovphysx/test/assets/test_articulation.py` — verbatim PhysX test mirror (~210 parametrizations) with PhysX-internal `root_view.X` assertions adapted to the OVPhysX bindings dict and `omni.physx.scripts`-dependent tests xfailed; mirrors the precedent from the RigidObject test mirror in isaac-sim#5426. ## Type of change - Breaking change (existing functionality will not work without user modification — OVPhysX is at `0.2.x`, clean break is acceptable per semver-on-0.x; no deprecation aliases for OVPhysX-introduced renames). - Code modernization / refactor. ## Validation Three layers, run on **GPU and CPU separately** (the wheel's process-global device-mode lock makes a single invocation lock to one device): 1. **Real-backend port** — `test_articulation.py` (verbatim PhysX mirror). `./scripts/run_ovphysx.sh -m pytest <path> -k 'cuda:0'` and `... -k 'cpu'`. Expected end state: each pass shows `<X> passed, <Y> xfailed, 0 failed`. Every xfail carries a `reason` pointing at the wheel-gaps spec. 2. **Cross-backend interface** — `source/isaaclab/test/assets/test_articulation_iface.py` will gain an `ovphysx` backend, mirroring the rigid-object iface treatment from isaac-sim#5426. 3. **API consistency audit** — per-method side-by-side checklist comparing Newton, RigidObject (post-refactor), and the rewritten Articulation; verifies method name, kwarg-only signature, parameter order, return type, docstring template, section-header placement. ## Status Active triage — not yet ready for review. - ✅ Implementation complete (all writers, setters, properties, lifecycle, actuator pipeline). - ✅ Initial GPU root-cause bug fixed: `_read_transform_binding` now routes `BODY_COM_POSE` through `_binding_read` so the wheel's CPU-only-binding device check is satisfied on a GPU sim. - ✅ Verbatim PhysX-internals assertions (`root_view.max_dofs == shared_metatype.dof_count`, `link_paths[0]` round-trip) adapted to the OVPhysX bindings dict — they now check `binding.shape[1] == num_joints / num_bodies` for each per-DOF / per-link binding. - 🔄 In-flight: tendon-init device-routing bug. `_read_initial_properties` reads `FIXED_TENDON_*` / `SPATIAL_TENDON_*` via numpy assuming CPU residency, but the wheel exposes them as GPU-resident (consistent with PhysX's `set_fixed_tendon_properties` not cloning to CPU). Plan is to remove tendon types from `_CPU_ONLY_TYPES` and read them directly into the sim-device buffer. - ⏳ Pending: cross-backend `test_articulation_iface.py` extension, API consistency audit, CHANGELOG + version bump (`0.2.x → 0.3.0`). ## Checklist - [x] I have read and understood the [contribution guidelines](https://isaac-sim.github.io/IsaacLab/main/source/refs/contributing.html) - [x] I have run the [`pre-commit` checks](https://pre-commit.com/) with `./isaaclab.sh --format` - [ ] I have made corresponding changes to the documentation - [ ] My changes generate no new warnings - [ ] I have added tests that prove my fix is effective or that my feature works (the verbatim PhysX test mirror is the contract; bug-fixing in progress) - [ ] I have updated the changelog and the corresponding version in the extension's `config/extension.toml` file (deferred to final-pass commit) - [x] I have added my name to the `CONTRIBUTORS.md` or my name already exists there --------- Signed-off-by: Kelly Guo <kellyg@nvidia.com> Co-authored-by: Kelly Guo <kellyg@nvidia.com>
matthewtrepte
pushed a commit
to matthewtrepte/IsaacLab
that referenced
this pull request
May 18, 2026
# Description Adds `OvPhysxSceneDataProvider`, the OVPhysX-backend implementation of `BaseSceneDataProvider`. Enables Newton-based visualizers (Rerun, Viser, native Newton viewport) to render OVPhysX simulations. Also fixes the `SceneDataProvider` factory dispatch (and adds a regression test) so the substring check `"physx" in "ovphysxmanager"` no longer routes ovphysx to PhysX. Fixes isaac-sim#5327 > [!IMPORTANT] > **Stacked on isaac-sim#5459** (`[OVPHYSX] Articulation rewrite`). The base of this PR is `develop`, so the diff includes every commit from isaac-sim#5459 — review only the 16 SDP-specific commits on top (`git log antoiner/feat/ovphysx_articulation..antoiner/feat/ovphysx_scene_data_provider`). Once isaac-sim#5459 merges, this PR will rebase cleanly. ## Architectural notes Mirrors `PhysxSceneDataProvider` end-to-end: build a Newton model from the scene's `ClonePlan` at init (gated on `SceneDataRequirement.requires_newton_model`), then on every `update()` read body poses through ovphysx `TensorBinding`s and write them into the Newton state's `body_q` via a single Warp kernel. The interesting OVPhysX-specific surface: - **One-pattern-per-binding**: the ovphysx wheel's `PhysX.create_tensor_binding` accepts a single glob-style pattern per binding (not a list, unlike PhysX's `RigidBodyView`). We bucket Newton body paths by their env-wildcard form (`/World/envs/env_*/Robot/cart`, `/World/envs/env_*/Robot/pole`, ...), one pose+velocity binding per distinct relative path. Cartpole produces 2 bindings; Allegro hand ~17 — each covering all envs. - **`RIGID_BODY_POSE` covers everything**: confirmed via standalone probe + wheel docs that the matcher accepts any prim with `UsdPhysics.RigidBodyAPI`, including articulation links. No separate `LINK_POSE` plumbing is needed. Paths flow through a `RigidBodyAPI` filter (mirroring `PhysxSceneDataProvider._setup_rigid_body_view` line ~281) so joints and articulation-root xforms are excluded from binding patterns. - **Wheel-0.4 `binding.read(dst)` API**: pre-allocated warp destination buffers, so per-step reads are allocation-free. - **View-order reorder**: each binding's `prim_paths` is matched against the Newton `body_label` ordering to build a per-binding reorder tensor with `-1` sentinels for rows owned by other bindings. The pose merge respects partial coverage across bindings, with `FrameView` fallback for anything that lacks `RigidBodyAPI` (cameras, decorative xforms). - **Factory fix**: `SceneDataProvider._get_backend` now checks `"ovphysx"` explicitly before `"physx"` so the substring overlap doesn't route the wrong backend. ## Files changed (16 commits since `antoiner/feat/ovphysx_articulation`) - `source/isaaclab/isaaclab/physics/scene_data_provider.py` — factory dispatch fix (+9/-1). - `source/isaaclab/test/sim/test_scene_data_provider_factory.py` — new parametrized regression test (44 lines). - `source/isaaclab_ovphysx/isaaclab_ovphysx/scene_data_providers/__init__.py`, `__init__.pyi` — package scaffolding. - `source/isaaclab_ovphysx/isaaclab_ovphysx/scene_data_providers/ovphysx_scene_data_provider.py` — the provider (~760 lines). - `source/isaaclab_ovphysx/test/scene_data_providers/test_ovphysx_scene_data_provider.py` — 18 stub-based unit tests covering factory dispatch, metadata, env discovery, Newton-model build, binding setup, pose-merge orchestration, transform/velocity getters, view-order reorder, camera-transform stage walk. - `docs/source/api/index.rst` + `docs/source/api/lab_ovphysx/isaaclab_ovphysx.scene_data_providers.rst` — first `isaaclab_ovphysx` section in the API reference. - `source/isaaclab/changelog.d/antoiner-feat-ovphysx-scene-data-provider.rst` — patch fragment for the factory fix. - `source/isaaclab_ovphysx/changelog.d/antoiner-feat-ovphysx-scene-data-provider.minor.rst` — minor fragment for the new provider. ## Type of change - New feature (non-breaking change which adds functionality). - Bug fix (factory dispatch). ## Validation 1. **Unit tests** — `./isaaclab.sh -p -m pytest source/isaaclab/test/sim/test_scene_data_provider_factory.py source/isaaclab_ovphysx/test/scene_data_providers/` → 23 passed. 2. **End-to-end** — `./isaaclab.sh -p scripts/reinforcement_learning/rsl_rl/train.py --task=Isaac-Cartpole-Direct-v0 --visualizer newton --num_envs 4096 presets=ovphysx` reaches the simulation loop; visualizer renders the cartpole scene. 3. **Pre-commit** — `./isaaclab.sh -f` clean. 4. **Pattern probe** — standalone reproduction at `/tmp/probe_rigid_body_pose_on_articulation.py` confirmed `RIGID_BODY_POSE` accepts articulation-link patterns. Reproducible against the wheel's bundled minimal articulation USD. ## Known follow-ups (not in this PR) - Extract `_build_newton_model_from_clone_plan` into a shared helper used by both PhysX and OVPhysX providers (currently a verbatim copy). - `FrameView` factory could grow an explicit `"ovphysx"` registration entry (today's dispatch falls through to the `"physx"` branch, which works because `FabricFrameView` reads from the shared USD stage). - Pattern length cap: if a scene's distinct-body-path count exceeds the wheel's per-pattern matcher limit (unknown), chunk into multiple bindings indexed by buffer-row offset. Hasn't bitten yet. - A future `test_ovphysx_scene_data_provider_visualizer_contract.py` mirroring `test_physx_scene_data_provider_visualizer_contract.py`. ## 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 feature works - [x] I have added a changelog fragment under `source/<pkg>/changelog.d/` for every touched package - [x] I have added my name to the `CONTRIBUTORS.md` or my name already exists there
AntoineRichard
added a commit
to AntoineRichard/IsaacLab
that referenced
this pull request
May 19, 2026
Drop AppLauncher and the PhysX-style setup_simulation fixture in favour of the kitless _ovphysx_sim_context helper (matches test_rigid_object.py shipped in isaac-sim#5459) and the autouse device-lock fixture for ovphysx<=0.3.7. Also drop the disable_contact_processing parametrize axis: toggling the global Carbonite '/physics/disableContactProcessing' flag requires the settings manager which is not available in kitless mode. test_no_contact_reporting now exercises the same semantic via a no-filter cfg instead. The three v2-deferred tests (track_friction_forces / track_contact_points) keep their pytest.mark.skip but their bodies are fully kitless so they can be un-skipped once the ovphysx wheel ships the missing per-sensor read APIs (see docs/superpowers/specs/2026-04-27-ovphysx-contact-api-gaps.md). Run via: ./scripts/run_ovphysx.sh -m pytest source/isaaclab_ovphysx/test/sensors/test_contact_sensor.py -v
AntoineRichard
added a commit
that referenced
this pull request
May 19, 2026
# Description Implements `RigidObjectCollection` and `RigidObjectCollectionData` for the OVPhysX backend, completing the rigid-body asset surface alongside `RigidObject` (#5426) and `Articulation` (#5459). The collection manages N distinct rigid bodies per environment with `(env, body)` dual indexing. The asset creates **one native fused TensorBinding per tensor type** via the ovphysx 0.4.3 `create_tensor_binding(prim_paths=[glob_0, …, glob_{B-1}])` API, mirroring how PhysX's `RigidBodyView` aggregates multiple body prims into a single flat view. Each binding spans `num_instances * num_bodies` prims and returns body-major flat data `(body_0_env_0, body_0_env_1, …, body_1_env_0, …)`. The data class and asset writers use strided-view reshape helpers (`_reshape_view_to_data_2d/_3d` and `reshape_data_to_view_2d/_3d`, ported from the PhysX collection) to convert between body-major view layout and the instance-major `(N, B, D)` layout exposed to users — no Warp kernels added, no per-body Python fan-out at runtime. Fixes #5317 **Stacked on:** - #5459 — OVPhysX `Articulation` - #5426 — OVPhysX `RigidObject` **Carries a one-commit cherry-pick of #5545's `ovphysx_manager.py` portion** (required for ovphysx 0.4 `active_cuda_gpus` API). Drop the cherry-pick once #5545 lands. ## Type of change - New feature (non-breaking change which adds functionality) ## Screenshots N/A — backend infrastructure, no visible behaviour 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 - [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 file under `source/isaaclab_ovphysx/changelog.d/`) - [x] I have added my name to the `CONTRIBUTORS.md` or my name already exists there ## Test plan Tested in a Docker container built from `docker/Dockerfile.base` (IsaacSim `6.0.0-dev2`) with the ovphysx 0.4.3 wheel installed: - `./scripts/run_ovphysx.sh -m pytest source/isaaclab/test/assets/test_rigid_object_collection_iface.py -k ovphysx` → **636 passed** - `./scripts/run_ovphysx.sh -m pytest source/isaaclab_ovphysx/test/assets/test_rigid_object_collection.py` → **72 passed, 76 skipped (device-mode lock — a second invocation with `-k 'cpu'` covers CPU), 4 xfailed** (material-properties gap shared with `RigidObject` until the wheel exposes `RIGID_BODY_MATERIAL`) - `./isaaclab.sh -f` → clean
AntoineRichard
added a commit
that referenced
this pull request
May 19, 2026
…5637) # Description Restructures the physics-backend documentation to give each backend a first-class home and to add the cross-backend orientation pages asked for in [isaac-sim/IsaacLab-Internal#876](isaac-sim/IsaacLab-Internal#876). **Structure** ``` docs/source/overview/core-concepts/physical-backends/ ├── index.rst ← user-facing hub + feature-support matrix ├── solver-comparison.rst ← cross-backend behavioural differences ├── physx/ │ ├── index.rst │ ├── installation.rst │ ├── configuration.rst ← PhysxCfg tuning knobs │ └── supported-features.rst ├── newton/ │ ├── index.rst │ ├── installation.rst │ ├── supported-features.rst (was experimental-features/.../limitations-and-known-bugs.rst) │ ├── mjwarp-solver.rst (was experimental-features/.../solver-transitioning.rst) │ └── kamino-solver.rst (was experimental-features/.../using-kamino.rst) └── ovphysx/ └── index.rst ← stub flagged as highly experimental; tracking issue #5634 ``` **Highlights** - The Newton subdir moves wholesale out of `experimental-features/` via `git mv`; framing changes from "experimental feature branch" to "beta backend." The Experimental Features toctree now contains only `bleeding-edge`. - Per-solver Newton pages (`mjwarp-solver`, `kamino-solver`) replace the old `solver-transitioning` / `using-kamino` files, matching #876's "sub-sections for the Newton solvers" ask. - New PhysX page set written from `isaaclab_physx.physics.PhysxCfg`, mirroring the Newton structure. - OvPhysX stub references the full in-flight PR set (#5421, #5422, #5426, #5459, #5570, #5589) and is gated by a follow-up issue (#5634) for expansion after those land. - `solver-comparison.rst` covers friction, contact pipeline, restitution, stabilization, convergence, articulation coordinates, substepping, and GPU buffers across PhysX TGS, Newton MJWarp, and Newton Kamino. Each cell points at the concrete config attribute that controls the behavior, with a porting checklist at the end. - Newton's `supported-features.rst` list refreshed against `develop`'s actual `newton_mjwarp` coverage (adds Shadow Hand, Shadow Hand Over, cabinet, dexsuite, rough-terrain locomotion). Replaces the bit-rotting bullet list with a discovery recipe (`grep -rln newton_mjwarp source/isaaclab_tasks/`). - Cross-references updated in `docs/index.rst`, `core-concepts/index.rst`, `multi_backend_architecture.rst`, `features/visualization.rst`, and `overview/reinforcement-learning/rl_existing_scripts.rst`. Fixes isaac-sim/IsaacLab-Internal#876 ## Type of change - Documentation update ## Screenshots N/A — docs-only restructure. New page tree visible from the table-of-contents in `core-concepts/`. ## 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 *(N/A — docs-only)* - [ ] I have added a changelog fragment under `source/<pkg>/changelog.d/` for every touched package *(N/A — docs-only; matches precedent of #5512 and 4aeb4d6 which shipped without fragments)* - [x] I have added my name to the `CONTRIBUTORS.md` or my name already exists there
AntoineRichard
added a commit
that referenced
this pull request
May 19, 2026
# Description Implements `ContactSensor`, `ContactSensorCfg`, and `ContactSensorData` for the `isaaclab_ovphysx` backend, mirroring the existing PhysX implementation. The contact sensor reports normal contact forces in the world frame using the ovphysx 0.3.7 `ContactBinding` API (`PhysX.create_contact_binding` / `read_net_forces` / `read_force_matrix`). Optional pose tracking is wired through a `RIGID_BODY_POSE` `TensorBinding`. Validation environment: `Isaac-Velocity-Flat-Anymal-C-Direct-v0` (Anymal-C foot-contact tracking for locomotion). **v1 scope (this PR):** - Net contact forces + history - Force matrix (filtered partner forces) + history - Pose tracking (`track_pose`) - Air/contact time tracking + `compute_first_contact` / `compute_first_air` - Reset semantics + native handle teardown on simulation stop **Deferred (raise `NotImplementedError` if cfg flag enabled):** - `track_contact_points` - `track_friction_forces` These features are blocked on tensor-friendly per-sensor read APIs in ovphysx (`ContactBinding.read_contact_points` / `read_friction_forces`). A maintainer-facing spec listing the missing APIs is attached at `docs/superpowers/specs/2026-04-27-ovphysx-contact-api-gaps.md`. The data properties still return `None` per the `BaseContactSensorData` contract; the implementation only raises if the cfg flag is set. Fixes #5325 Parent issue: #5315 **Stacked on:** - #5459 (`[OVPHYSX] Articulation rewrite`) — this branch is rebased on top of `antoiner/feat/ovphysx_articulation`. Reviewers can focus on the last 13 commits (everything from `Scaffold isaaclab_ovphysx sensors sub-package` onward); commits before that are inherited from #5459. Will be re-rebased on `develop` once #5459 merges. **Dependencies:** - Requires #4852 (merged into `develop` 2026-04-20). - ovphysx `RigidObject` lands as part of #5459 — no separate gate. ## Type of change - New feature (non-breaking change which adds functionality) ## Screenshots N/A — backend feature, no UI surface. ## 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 fragment at `source/isaaclab_ovphysx/changelog.d/antoiner-feat-ovphysx_contactsensor.minor.rst`, docstrings, gap spec for the maintainer of ovphysx) - [x] My changes generate no new warnings - [x] I have added tests that prove my feature works (9 tests adapted from the PhysX backend; 3 skipped for the deferred features so they're trivially un-skip-able once ovphysx ships the missing APIs) - [x] I have updated the changelog and the corresponding version in the extension's `config/extension.toml` file (changelog fragment, minor tier — version bump compiled by the nightly CI workflow per the upstream convention) - [x] I have added my name to the `CONTRIBUTORS.md` or my name already exists there ## Notes for the reviewer - The Warp kernels (`sensors/contact_sensor/kernels.py` and the shared `sensors/kernels.py`) are physics-engine-agnostic and ported verbatim from the PhysX backend — only module docstrings differ. - `ContactSensorCfg` and `ContactSensorData` are also near-verbatim mirrors; the only edits are the backend-specific `class_type` pointer and the shared-kernels import path. - The ovphysx-specific glue lives in `_initialize_impl` (USD prim discovery + regex→fnmatch glob conversion + `create_contact_binding` + optional `RIGID_BODY_POSE` binding), `_create_buffers` (pre-allocated DLPack read buffers), `_update_buffers_impl` (per-step reads), and `_invalidate_initialize_callback` (native handle release). - **Tests not yet executed.** They are currently authored in the Isaac-Sim/`AppLauncher` style (mirroring `isaaclab_physx/test/sensors/test_contact_sensor.py`); they need to be re-adapted to the kitless `./scripts/run_ovphysx.sh -m pytest` flow and the `_ovphysx_sim_context` helper used by the articulation/rigid-object suites in #5459. Will land as a follow-up commit on this branch once that adaptation is reviewed.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Description
Drastic rewrite of OVPhysX
ArticulationandArticulationDataso they follow the same shape as the post-refactor OVPhysXRigidObjectfrom #5426, with the API surface mirroringNewton Articulationand behavior parity withPhysX Articulation. Single-PR atomic rewrite, clean break (no deprecation aliases for OVPhysX-introduced renames; framework-inherited deprecated shims kept).The OVPhysX articulation diverged significantly from the rest of the framework conventions. This PR brings it back in line: same docstring template, same section ordering, same naming, same internal patterns, same lifecycle.
Important
Stacked on #5426 (
[OVPHYSX] RigidObject + RigidObjectData asset). Review only the 16 articulation-specific commits at the tip of this branch — every commit before that lands via #5426. Once #5426 merges todevelop, this PR will rebase cleanly ontodevelop.Fixes # (none — internal refactor; no associated issue)
Architectural changes
OVPhysX RigidObject is the design template. It has navigated the hybrid OVPhysX surface — Newton-style mask+index dual API + PhysX-style CPU-only bindings via pinned-host staging à la #5329 + pull-to-refresh
binding.read(target):TimestampedBufferWarpallocation in_create_buffers(single source of truth — no_invalidate_caches/_ensure_*_buffersmachinery)._binding_read/_binding_write/_stage_to_pinned_cpuhelpers route CPU-only types through pinned-host memory.ProxyArray(warp + torch dual view); rawwp.arrayfor one-shot config buffers.num_instances,num_bodies,num_joints,body_names,joint_names, ...) demoted from@propertyto plain instance attributes.*_indexaccepts partial data;*_maskaccepts full data with awp.boolmask).write_*/set_*parameters are kwarg-only after*,. No positional. Nofull_dataflag anywhere._write_body_stateplumbing layer is removed; deprecated state-writer shims (write_root_state_to_sim, etc.) call the publicwrite_*_to_sim_indexmethods directly, mirroring RigidObject.Articulation-specific surface mirrors Newton 1-to-1: joint-state writers, joint-property writers (CPU-only), body-property setters (multi-body shape), joint-command target setters, external-wrench setters via
WrenchComposer, fixed/spatial tendon setters, deprecated state-writer shims, full actuator pipeline (compute,_apply_actuator_model,_process_actuators_cfg).Files changed
source/isaaclab_ovphysx/isaaclab_ovphysx/assets/articulation/articulation.py— full rewrite (~3863 lines, matches Newton).source/isaaclab_ovphysx/isaaclab_ovphysx/assets/articulation/articulation_data.py— full rewrite (~2504 lines).source/isaaclab_ovphysx/isaaclab_ovphysx/assets/kernels.py— gained 6 articulation kernels migrated from the stop-gapkernels_old.py(now deleted):_compose_root_com_pose,_compute_heading,_copy_first_body,_projected_gravity,_world_vel_to_body_ang,_world_vel_to_body_lin. Plus 2 new joint-property kernels (write_joint_position_limit_to_buffer_index/maskfor trailing-dim-2 limits,write_joint_friction_to_buffer_index/maskfor the broadcast-coefficient pattern).source/isaaclab_ovphysx/isaaclab_ovphysx/assets/kernels_old.py— deleted.source/isaaclab_ovphysx/test/assets/test_articulation.py— verbatim PhysX test mirror (~210 parametrizations) with PhysX-internalroot_view.Xassertions adapted to the OVPhysX bindings dict andomni.physx.scripts-dependent tests xfailed; mirrors the precedent from the RigidObject test mirror in [OVPHYSX] RigidObject + RigidObjectData asset #5426.Type of change
0.2.x, clean break is acceptable per semver-on-0.x; no deprecation aliases for OVPhysX-introduced renames).Validation
Three layers, run on GPU and CPU separately (the wheel's process-global device-mode lock makes a single invocation lock to one device):
test_articulation.py(verbatim PhysX mirror)../scripts/run_ovphysx.sh -m pytest <path> -k 'cuda:0'and... -k 'cpu'. Expected end state: each pass shows<X> passed, <Y> xfailed, 0 failed. Every xfail carries areasonpointing at the wheel-gaps spec.source/isaaclab/test/assets/test_articulation_iface.pywill gain anovphysxbackend, mirroring the rigid-object iface treatment from [OVPHYSX] RigidObject + RigidObjectData asset #5426.Status
Active triage — not yet ready for review.
_read_transform_bindingnow routesBODY_COM_POSEthrough_binding_readso the wheel's CPU-only-binding device check is satisfied on a GPU sim.root_view.max_dofs == shared_metatype.dof_count,link_paths[0]round-trip) adapted to the OVPhysX bindings dict — they now checkbinding.shape[1] == num_joints / num_bodiesfor each per-DOF / per-link binding._read_initial_propertiesreadsFIXED_TENDON_*/SPATIAL_TENDON_*via numpy assuming CPU residency, but the wheel exposes them as GPU-resident (consistent with PhysX'sset_fixed_tendon_propertiesnot cloning to CPU). Plan is to remove tendon types from_CPU_ONLY_TYPESand read them directly into the sim-device buffer.test_articulation_iface.pyextension, API consistency audit, CHANGELOG + version bump (0.2.x → 0.3.0).Checklist
pre-commitchecks with./isaaclab.sh --formatconfig/extension.tomlfile (deferred to final-pass commit)CONTRIBUTORS.mdor my name already exists there