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

2026-02-27

AI Summary

This work addresses the poor generalization of existing learning-based path planning methods when training and test environments exhibit differing map distributions. To overcome this limitation, the authors propose a universal, learnable heuristic predictor that leverages a deep neural network to model obstacle configurations and integrates seamlessly with A* search to form an end-to-end trainable heuristic function. This approach is the first to achieve generalization across topologically heterogeneous environments, eliminating reliance on the common assumption of identical training and test distributions. Experimental results demonstrate that, in completely unseen test scenarios, the method reduces A*’s computational overhead by up to 2.2× while maintaining solution quality within an average of 3% of the optimal path cost.

Technology Category

• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Search and Optimization: Learning to Search
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• grid-based pathfinding
• out-of-distribution generalization
• universal planner
• heuristic learning
• topological heterogeneity

Innovation

• universal planner
• grid-based pathfinding
• learned heuristic
• out-of-distribution generalization
• deep neural networks