SGIS-RC: Bio-Inspired Identifiability-Aware Single-Anchor Scalar-Range Compensation

Biological control often combines selective sensing, complementary response scales, and attenuation under weak evidence. Guided by these principles, this paper presents Spectrum-Guided Identifiable Single-Anchor Range Compensation (SGIS-RC), a deterministic physics–data framework for single-anchor scalar-range compensation. SGIS-RC removes the local anchor–bias nuisance tangent from the kinematic sensitivity, retains a numerically conditioned physical subspace, and models the remaining discrepancy through a Chebyshev–Matérn global–local residual field. The learned correction is further regulated by leverage, configuration-space support, and bounded amplitude control. On two public workbooks, ABB IRB120 and HSR-C JR680, a pre-specified outer-partition evaluation performed after the model specification was frozen yielded configuration-group MAEs of 0.2306±0.0148 mm and 0.0493±0.0021 mm, respectively, while the matched conventional hybrid yielded slightly lower mean errors of 0.2244±0.0151 mm and 0.0478±0.0015 mm. Same-fit analyses show that support placement can alter the balance between global and local residual correction, and the block protocols indicate that support-shift behavior remains dataset dependent. Overall, SGIS-RC provides a structured and auditable framework that integrates identifiability-aware physical adaptation, global–local residual modeling, and support-aware deployment control for single-anchor scalar-range compensation.