Graph Neural Networks for Motion Planning
It addresses motion planning for robotics, but appears incremental as it applies GNNs to an existing domain.
This paper tackles motion planning problems by using Graph Neural Networks (GNNs) to guide algorithms, showing that GNNs improve over traditional analytic methods and other neural network approaches in experiments with critical sampling, a pendulum, and a six DoF robot arm.
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.