Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Search

TL;DR

This paper introduces a hybrid path-planning method combining graph neural networks with an optimized branch and bound search, significantly improving speed and scalability in constrained environments for autonomous vehicles.

Contribution

It presents a novel hybrid approach that integrates graph neural networks with branch and bound algorithms for efficient constrained path planning.

Findings

Substantial speedup in path planning tasks.

Outperforms handcrafted heuristics in complex scenarios.

Enables smoother scaling to harder problems.

Abstract

Deep learning-based methods are growing prominence for planning purposes. In this paper, we present a hybrid planner that combines a graph machine learning model and an optimal solver based on branch and bound tree search for path-planning tasks. More specifically, a graph neural network is used to assist the branch and bound algorithm in handling constraints associated with a desired solution path. There are multiple downstream practical applications, such as Autonomous Unmanned Ground Vehicles (AUGV), typically deployed in disaster relief or search and rescue operations. In off-road environments, AUGVs must dynamically optimize a source-destination path under various operational constraints, out of which several are difficult to predict in advance and need to be addressed online. We conduct experiments on realistic scenarios and show that graph neural network support enables substantial speedup and smoother scaling to harder path-planning problems. Additionally, information provided by the graph neural network enables the approach to outperform problem-specific handcrafted heuristics, highlighting the potential graph neural networks hold for path-planning tasks.