[ooctipus]

OperationalSpaceControllerAction and the OSC integration-test helper used link-origin poses and Jacobians together with center-of-mass velocity feedback. When a link rotates with an offset center of mass, these quantities describe different points, producing incorrect velocity feedback. The task-frame test also copied rounded command quaternions directly into reference frames, producing inconsistent composed targets.

Use body_link_vel_w and root_link_vel_w in both OSC callers, and normalize the test's cloned task-frame quaternion before coordinate conversion. Controller gains, raw command fixtures, convergence tolerances, and step budgets match the base branch; the nullspace damping ratio remains 1.0.

Two direct regressions guard these contracts: a moving, fixed-base Franka checks each caller's velocity against its link Jacobian multiplied by measured joint velocity, and a numerical check verifies that the same rounded command resolves to the same absolute target through root and task frames without mutating its inputs.

Provenance:

• #5400 migrated both OSC callers to body_link_jacobian_w while retaining the COM velocity accessors.
• The rounded fixtures and unnormalized task-frame copy originated in #913. #7624 later normalized absolute pose commands, while the separately supplied frame remained unnormalized. The exact change that first exposed the convergence failures has not been bisected; these references establish the input inconsistencies, not the first failing CI run.

Validation:

• Restoring COM feedback makes both velocity regression cases fail, with a maximum linear-velocity discrepancy of 0.01469 m/s versus the 1e-4 assertion tolerance. Both pass with link-origin feedback.
• Removing frame normalization makes the target-equivalence regression fail with a quaternion-component discrepancy of 0.00010675 versus the 1e-6 tolerance. It passes with the correction.
• The previously failing test_franka_taskframe_pose_abs and original test_franka_pose_abs_with_nullspace_centering both pass with damping 1.0.
• Full OSC integration file: 21 passed in 113 seconds, including all three new regression cases.
• uv run isaaclab -f passes.

The earlier RL, legacy-rendering, and contrib failures have matching failures and passing corresponding jobs in separate fixes: #7870, #7871, and #7866, respectively. Those fixes remain separate from these OSC corrections.

[isaaclab-review-bot]

Isaac Lab Review Bot

The patch makes a focused test-only correction: it normalizes task-frame quaternion fixtures, increases damping for the nullspace-centering pose test, and switches velocity feedback to link-origin quantities consistent with the pose and Jacobian used by _update_states.

• Design and architecture: The feedback path now consistently uses link-origin pose, Jacobian, and velocity data. The damping adjustment remains scoped to one test configuration and does not alter the operational-space controller implementation.
• API: No public APIs, defaults, exports, or documented runtime behavior are changed. The edits are confined to test fixtures and a private test helper, with an appropriate .skip changelog fragment.
• Implementation: The quaternion fixtures are normalized before use, and the changed velocity producer matches the existing link-origin consumers. Increasing the damping ratio from 1.0 to 2.0 reduces coverage of the less-damped convergence regime, but this is a non-blocking tradeoff for stabilizing the large-step nullspace-centering test.

No blocking issues. No inline issue met the actionable-evidence threshold; the assessment above records the review feedback.

Automated review; human maintainers own approval decisions.

[greptile-apps]

Confidence Score: 5/5

The PR appears safe to merge, with the test feedback and fixtures now using consistent reference points and valid task-frame orientations.

Summary

This PR corrects operational-space controller integration-test fixtures and feedback without changing the controller implementation, convergence tolerances, or simulation budgets.

• Normalizes absolute-pose quaternion fixtures before they are reused as task-frame orientations.
• Uses link-origin end-effector and root velocities consistently with the link-origin pose and Jacobian.
• Increases task damping for the large nullspace-centering pose steps.
• Adds a changelog fragment describing the test stabilization.

_{Reviews (1) · Last reviewed commit: "Correct operational-space controller tes..."}

[maxkra15]

run-ci

[ooctipus]

run-ci

[kellyguo11]

run-ci