dsfb-robotics 0.1.0

DSFB Structural Semiotics Engine for Robotics Health Monitoring — a deterministic, non-intrusive observer layer that reads the residuals existing robot control, kinematic identification, and whole-body balance observers already compute, and structures them into a human-readable grammar of typed episodes. Read-only augmentation, not replacement, of incumbent PHM / FDD / MPC / observer pipelines.
Documentation
dsfb-robotics
Copyright 2026 Invariant Forge LLC

This product includes software developed by Invariant Forge LLC.

IP Notice
---------

The theoretical framework, formal constructions, and supervisory methods
described herein constitute proprietary Background IP of Invariant Forge LLC
(Delaware LLC No. 10529072), with prior art established by this publication
and earlier Zenodo DOI publications by the same author. Commercial deployment
requires a separate written license. Reference implementations are released
under Apache 2.0.

Licensing: licensing@invariantforge.net

Dataset Attribution
-------------------

This crate's companion paper evaluates the DSFB observer on ten public
robotics and prognostics datasets. Each dataset retains its own upstream
licence. The dsfb-robotics crate redistributes only stratified slices (or,
where upstream terms require, manifest-only pointers with SHA-256 checksums)
under the original dataset licences. Full datasets must be obtained by the
user from the original providers under those providers' terms. See
`data/slices/SLICE_MANIFEST.json` and the per-dataset oracle-protocol
documents under `docs/` for provenance, licence, and fetch instructions.