Neural-Guided RuntimePrediction of Planners for Improved Motion and Task Planning with Graph Neural Networks

TL;DR

This paper uses graph neural networks to predict the runtime of sampling-based motion planners based on problem structure, enabling more efficient planning and problem decomposition in navigation and manipulation tasks.

Contribution

It introduces a GNN-based approach to predict motion planning runtimes, improving online planning efficiency and problem decomposition in complex robotic tasks.

Findings

GNNs accurately predict SBMP runtime based on problem structure

Predictions enable faster online motion planning in navigation and manipulation

The approach generalizes from low-dimensional to high-degree-of-freedom tasks

Abstract

The past decade has amply demonstrated the remarkable functionality that can be realized by learning complex input/output relationships. Algorithmically, one of the most important and opaque relationships is that between a problem's structure and an effective solution method. Here, we quantitatively connect the structure of a planning problem to the performance of a given sampling-based motion planning (SBMP) algorithm. We demonstrate that the geometric relationships of motion planning problems can be well captured by graph neural networks (GNNs) to predict SBMP runtime. By using an algorithm portfolio we show that GNN predictions of runtime on particular problems can be leveraged to accelerate online motion planning in both navigation and manipulation tasks. Moreover, the problem-to-runtime map can be inverted to identify subproblems easier to solve by particular SBMPs. We provide a motivating example of how this knowledge may be used to improve integrated task and motion planning on simulated examples. These successes rely on the relational structure of GNNs to capture scalable generalization from low-dimensional navigation tasks to high degree-of-freedom manipulation tasks in 3d environments.