Skip to content

Add continuous shoe grip checks and publish paired benchmark - #19

Open
Tarzelf wants to merge 2 commits into
feat/skill-prerequisites-v01from
feat/continuous-shoe-grip-v02
Open

Tarzelf wants to merge 2 commits into
feat/skill-prerequisites-v01from
feat/continuous-shoe-grip-v02

Conversation

@Tarzelf

@Tarzelf Tarzelf commented Oct 13, 2026

Copy link
Copy Markdown
Contributor

The mounted-rake shoe task previously checked retention only at the end. This adds continuous acquisition/contact-loss monitoring, a 40 mm TCP-travel checkpoint during lifting, and supported lowering before one recentered regrasp. The original arm, tool, workspace and shoe dynamics stay paired with the baseline.

The frozen fresh comparison is 2/10 retained lifts under both controllers, on the same cases, with all 20 attempts valid. Twelve lowering responses across six failed grasp cases produce no additional completed lifts and add 34.02 simulated seconds. An independent audit verifies nine bilateral-loss alarms at 20–52 ms of simulated time; this is not hardware response latency. The final scorer excludes table, rake and other robot support and checks every native tick of the last 500 ms.

This PR also adds a CPU benchmark CLI, recorded 3D comparison viewer, a sealed fresh protocol, complete native trace exports, a publication adapter for the separate v0.2 namespace, development/regression records and independent audit. The policies are authored and observe privileged simulator state. The benchmark is not a learned skill or physical-robot qualification.

  • Frozen implementation: af8933994b4626e28a0554abc782ae9d22cff06c; subsequent commits document results without changing that implementation.
  • Validation: 45 native/reporting tests and 19 publisher tests passed locally; responsive layout, playback, event seek, policy/case selection, collision view, completed lift and short-tool deferral checked in the browser.
  • Historical regression: 18/18 valid; both controllers retain the same 1/9 completion.
  • Results and full evidence · Hugging Face comparison

Stacked on #18 to keep this review focused on the continuous-grip change.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant