DVIDIA RESEARCH · NATIVE CONTACT TASK

Grasp. Carry. Release. Measure.

Authored, privileged-state rigid-block task in native reference physics. No learned policy, shoe physics, human-video action recovery or physical robot qualification.

A free rigid block must be lifted, placed near a separate target, released and left settled with the tool retreated. The scorer uses native object state independently of the controller’s phase. The block is never welded to the gripper.

Full summary · Frozen protocol · Artifact hashes

Every planned attempt

18 attempts · confirmation cohort. Synthetic scenarios; counts do not establish physical reliability.

SceneControllerOutcomeReasonFinal error · mmFirst dwell · sWall · sEvidence
nominal-00placementCompletedsuccess0.4911.235.35Attempt JSON
nominal-00replay_open_jawFailedtimeout188.34—2.37Attempt JSON
nominal-00holdFailedtimeout188.34—3.36Attempt JSON
nominal-01placementCompletedsuccess0.5011.312.97Attempt JSON
nominal-01replay_open_jawFailedtimeout199.09—3.70Attempt JSON
nominal-01holdFailedtimeout199.09—2.83Attempt JSON
nominal-02placementCompletedsuccess0.5111.353.11Attempt JSON
nominal-02replay_open_jawFailedtimeout202.74—8.38Attempt JSON
nominal-02holdFailedtimeout202.74—15.84Attempt JSON
nominal-03placementCompletedsuccess0.5111.4329.51Attempt JSON
nominal-03replay_open_jawFailedtimeout206.72—27.04Attempt JSON
nominal-03holdFailedtimeout206.72—5.64Attempt JSON
low_friction-00placementCompletedsuccess0.5311.376.61Attempt JSON
low_friction-00replay_open_jawFailedtimeout204.72—3.72Attempt JSON
low_friction-00holdFailedtimeout204.72—4.27Attempt JSON
low_friction-01placementCompletedsuccess0.5511.614.66Attempt JSON
low_friction-01replay_open_jawFailedtimeout221.60—6.83Attempt JSON
low_friction-01holdFailedtimeout221.60—4.95Attempt JSON

What this advances

This environment provides a task and negative controls for a future small DVIDIA action policy. Footage review, robot actions, learned control and physical qualification remain separate stages. Rigid-block contact does not validate a soft shoe, laces or a real gripper.

Runtime and timing scope

Attempt wall time includes asset checks, compilation, reset, planning, stepping and trace capture; separate inner timings identify narrower boundaries. No rendering, sensing, training, disk serialization, transport or physical actuation.

{"platform": "macOS-26.5.2-arm64-arm-64bit", "machine": "arm64", "python": "3.12.9", "mujoco": "3.15.0", "gpu_used": false, "logical_cpu_count": 10, "process_lifetime_peak_rss_bytes": 531054592, "memory_scope": "Process lifetime high-water resident memory including imports, native models and traces, before final bundle inspection or replay export; not per-episode memory or minimum RAM. Null means unavailable."}

Each attempt retains its timing distribution, complete states, requested commands and outcome measurements. Warm model inference and camera-to-actuator latency are not measured by this authored-controller benchmark.