Repository navigation
Conversation
This was referenced Oct 13, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
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.
af8933994b4626e28a0554abc782ae9d22cff06c; subsequent commits document results without changing that implementation.Stacked on #18 to keep this review focused on the continuous-grip change.