Reproduce “Mixture of Flow Matching and Particle Filter for Proprioception-Based Online Contact Estimation” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Seo Wook Han, Min Jun Kim
ContactFlowFilter estimates one or two robot contacts by combining a recursive particle filter with flow-matching proposals from sensor observations. Its measurement model also estimates forces. On real-robot dual-contact trials, M-RMSE, the average nearest-particle distance across contacts, was 0.88 ± 2.31 cm, versus 5.49 ± 11.36 cm for CPF. Nearby contacts may remain indistinguishable.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.