Graph Neural Networks for Motion Planning

Abstract

This paper investigates the feasibility of using Graph Neural Networks (GNNs) for classical motion planning problems. We propose guiding both continuous and discrete planning algorithms using GNNs' ability to robustly encode the topology of the planning space using a property called permutation invariance. We present two techniques, GNNs over dense fixed graphs for low-dimensional problems and sampling-based GNNs for high-dimensional problems. We examine the ability of a GNN to tackle planning problems such as identifying critical nodes or learning the sampling distribution in Rapidly-exploring Random Trees (RRT). Experiments with critical sampling, a pendulum and a six DoF robot arm show GNNs improve on traditional analytic methods as well as learning approaches using fully-connected or convolutional neural networks.

References in corpus (5)

• Semi-Supervised Classification with Graph Convolutional Networks
• Convolutional Neural Network Architectures for Signals Supported on Graphs
• Stability Properties of Graph Neural Networks
• Graph Policy Gradients for Large Scale Robot Control
• Graph Policy Gradients for Large Scale Unlabeled Motion Planning with Constraints

Cited by in corpus (3)

• Multi-Robot Collaborative Perception with Graph Neural Networks
• Input State Stability of Gated Graph Neural Networks
• Guided Incremental Local Densification for Accelerated Sampling-based Motion Planning