Research

Paper

TESTING February 27, 2026

UPath: Universal Planner Across Topological Heterogeneity For Grid-Based Pathfinding

Authors

Aleksandr Ananikian, Daniil Drozdov, Konstantin Yakovlev

Abstract

The performance of search algorithms for grid-based pathfinding, e.g. A*, critically depends on the heuristic function that is used to focus the search. Recent studies have shown that informed heuristics that take the positions/shapes of the obstacles into account can be approximated with the deep neural networks. Unfortunately, the existing learning-based approaches mostly rely on the assumption that training and test grid maps are drawn from the same distribution (e.g., city maps, indoor maps, etc.) and perform poorly on out-of-distribution tasks. This naturally limits their application in practice when often a universal solver is needed that is capable of efficiently handling any problem instance. In this work, we close this gap by designing an universal heuristic predictor: a model trained once, but capable of generalizing across a full spectrum of unseen tasks. Our extensive empirical evaluation shows that the suggested approach halves the computational effort of A* by up to a factor of 2.2, while still providing solutions within 3% of the optimal cost on average altogether on the tasks that are completely different from the ones used for training $\unicode{x2013}$ a milestone reached for the first time by a learnable solver.

Metadata

arXiv ID: 2602.23789
Provider: ARXIV
Primary Category: cs.LG
Published: 2026-02-27
Fetched: 2026-03-02 06:04

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.23789v1</id>\n    <title>UPath: Universal Planner Across Topological Heterogeneity For Grid-Based Pathfinding</title>\n    <updated>2026-02-27T08:34:56Z</updated>\n    <link href='https://arxiv.org/abs/2602.23789v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.23789v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>The performance of search algorithms for grid-based pathfinding, e.g. A*, critically depends on the heuristic function that is used to focus the search. Recent studies have shown that informed heuristics that take the positions/shapes of the obstacles into account can be approximated with the deep neural networks. Unfortunately, the existing learning-based approaches mostly rely on the assumption that training and test grid maps are drawn from the same distribution (e.g., city maps, indoor maps, etc.) and perform poorly on out-of-distribution tasks. This naturally limits their application in practice when often a universal solver is needed that is capable of efficiently handling any problem instance. In this work, we close this gap by designing an universal heuristic predictor: a model trained once, but capable of generalizing across a full spectrum of unseen tasks. Our extensive empirical evaluation shows that the suggested approach halves the computational effort of A* by up to a factor of 2.2, while still providing solutions within 3% of the optimal cost on average altogether on the tasks that are completely different from the ones used for training $\\unicode{x2013}$ a milestone reached for the first time by a learnable solver.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-02-27T08:34:56Z</published>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Aleksandr Ananikian</name>\n      <arxiv:affiliation>Saint-Petersburg University</arxiv:affiliation>\n    </author>\n    <author>\n      <name>Daniil Drozdov</name>\n      <arxiv:affiliation>Saint-Petersburg University</arxiv:affiliation>\n    </author>\n    <author>\n      <name>Konstantin Yakovlev</name>\n      <arxiv:affiliation>Saint-Petersburg University</arxiv:affiliation>\n    </author>\n  </entry>"
}