Generalizable Friction Coefficient Estimation via Material Embedding and Proxy Interaction Modeling
TLDR
This paper introduces a proxy-based framework to estimate friction coefficients between arbitrary materials using learned embeddings, significantly reducing testing.
Key contributions
- Introduces a proxy-based framework to approximate pairwise friction using a fixed set of proxy materials.
- Learns per-material embeddings and a fusion function to predict friction coefficients.
- Presents deterministic and probabilistic models, proxy selection, and handling of noisy data.
- Achieves high accuracy and reduces experimental testing on simulated and real friction datasets.
Why it matters
Accurate friction estimation is crucial for robotics and simulation. This method drastically cuts down on the extensive pairwise testing traditionally required, making material characterization more efficient and scalable. It also provides interpretable embeddings and uncertainty estimates.
Original 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 $f(A,B)$ from a small, fixed set of proxy materials $C=[c_1,\dots,c_k]$ by learning a per-material embedding $z_A = g(f(A,c1),\dots,f(A,ck))$ and a fusion function $p$ such that $f(A,B)\approx p\big(z_A,z_B\big)$. We present deterministic and probabilistic realizations of $g$ and $p$, 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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.