A horizon-agnostic neural operator paired with a boundary control barrier function creates a real-time safety filter that raises safe trajectory rates by up to 22% on fluid manipulation tasks in simulation.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Proves L2 exponential stability of geometric heat flow under bounded curvature with always-guaranteed asymptotic convergence, plus a Chebyshev pseudospectral solver for millisecond geodesic computation verified on surfaces and in a contraction controller.
citing papers explorer
-
Online Safety Filter for Deformable Object Manipulation with Horizon Agnostic Neural Operators
A horizon-agnostic neural operator paired with a boundary control barrier function creates a real-time safety filter that raises safe trajectory rates by up to 22% on fluid manipulation tasks in simulation.
-
Analysis of the Geometric Heat Flow Equation: Computing Geodesics in Real-Time with Convergence Guarantees
Proves L2 exponential stability of geometric heat flow under bounded curvature with always-guaranteed asymptotic convergence, plus a Chebyshev pseudospectral solver for millisecond geodesic computation verified on surfaces and in a contraction controller.