cs.ROApr 27, 2026

Generalizable Friction Coefficient Estimation via Material Embedding and Proxy Interaction Modeling

Authors: Zhendong WangHuamin Wang

Organizations: Style3D Research Hangzhou, China

Abstract

Accurately estimating friction coefficients between arbitrary material pairs is critical for robotics, digital fabrication, and physics-based simulation, but exhaustive pairwise testing scales quadratically with the number of materials. We introduce a proxy-based modeling framework that approximates any pairwise friction f(A,B)f(A,B) from a small, fixed set of proxy materials C=[c1,,ck]C=[c_1,\dots,c_k] by learning a per-material embedding zA=g(f(A,c1),,f(A,ck))z_A = g(f(A,c1),\dots,f(A,ck)) and a fusion function pp such that f(A,B)p(zA,zB)f(A,B)\approx p\big(z_A,z_B\big). We present deterministic and probabilistic realizations of gg and pp, procedures for selecting diverse proxy sets, and mechanisms for handling missing or noisy proxy measurements. The learned embeddings are compact, interpretable, and enable calibrated uncertainty estimates for downstream decision making. On simulated and measured friction datasets, our approach achieves high predictive accuracy, robust performance with partial observations, and substantial experimental savings by significantly reducing pairwise testing.

Explore similar work

CardsList
  1. A Splitting Architecture for Exact Reduced Coulomb Friction

    Jul 21, 2026Hongcheng Song, Ye Fan, Uri M. Ascher +1FrictionContact Forces