docs(nav): document the two-head sigmoid material reroute + the ext_force boundary - #471
Merged
Merged
Conversation
…orce boundary NAV_MATERIAL.md documented only the single-softplus has_lam() reroute (4th output overrides lam_soft). Document the shipping two-head form (#436): - deploy table: add the 5-output kFlagLamSigmoid net (4th/5th = lam_soft/lam_hard, each lam_max*sigmoid, .cvcnav format v2); - a paragraph on the two-head sigmoid reroute — why sigmoid bounding (clean channel suppression), the lam_soft_max/lam_hard_max ceilings (5/10) stored in the v2 trailer, the pre-v2 host hard-fail, pinned by nav_material_deploy_test; - a short boundary note: cvc::nav is force-agnostic (the ext_force port knows only 'a force at a pose'), so the two-head channel is a reusable template a downstream layer can re-source through the same seam without touching this core.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
docs/NAV_MATERIAL.mddocumented only the single-softplushas_lam()reroute (4th output overridinglam_soft). The shipping two-head sigmoid reroute (#436) —kFlagLamSigmoid, 5th outputlam_hard,λ_max·σ,.cvcnavformat v2 — was undocumented. Docs-only.Changes
kFlagLamSigmoidnet row (4th/5th =lam_soft/lam_hard, each sigmoid-boundedλ_max·σ(·),.cvcnavformat v2).λ→0), thelam_soft_max/lam_hard_maxceilings (5/10) stored in the v2 trailer, the pre-v2-host hard-fail, and thenav_material_deploy_testround-trip.cvc::navis force-agnostic — theext_forceport knows only "a force field at a pose", so the two-head soft/hard channel is a reusable template a downstream layer can re-source through the same seam without any change here (consistent with the existingNAV_STATS.mdframing).No new external-force specifics; the note only makes explicit the seam already described in this file and
NAV_STATS.md. (Supersedes the auto-closed #470, whose branch was renamed off anrf-tagged name.)