Neural-NF learns a mapping from intrinsic Laplacian features to local PDE coefficients whose solution yields a collision-free, monotonically descending navigation function with global goal minimum by construction, achieving up to 5x better zero-shot transfer than direct value-function predictors.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A shifted interface method is extended to transient poroelasticity, enabling first-order accurate modeling of embedded cracks on unfitted meshes with weak or strong interface enforcement.
citing papers explorer
-
Neural Navigation Functions for Zero-Shot Generalizable Motion Planning
Neural-NF learns a mapping from intrinsic Laplacian features to local PDE coefficients whose solution yields a collision-free, monotonically descending navigation function with global goal minimum by construction, achieving up to 5x better zero-shot transfer than direct value-function predictors.
-
A shifted interface approach for internal discontinuities in poroelastic media
A shifted interface method is extended to transient poroelasticity, enabling first-order accurate modeling of embedded cracks on unfitted meshes with weak or strong interface enforcement.