Complex-Valued GNNs for Distributed Basis-Invariant Control of Planar Systems
This addresses the limitation of current GNN controllers for networked dynamical systems in environments without GPS or compasses, representing an incremental advance in domain-specific control methods.
The paper tackled the problem of distributed control in GPS-denied environments by developing a complex-valued GNN architecture that is invariant to local basis choices, resulting in improved data efficiency, tracking performance, and generalization in a flocking task compared to a real-valued baseline.
Graph neural networks (GNNs) are a well-regarded tool for learned control of networked dynamical systems due to their ability to be deployed in a distributed manner. However, current distributed GNN architectures assume that all nodes in the network collect geometric observations in compatible bases, which limits the usefulness of such controllers in GPS-denied and compass-denied environments. This paper presents a GNN parametrization that is globally invariant to choice of local basis. 2D geometric features and transformations between bases are expressed in the complex domain. Inside each GNN layer, complex-valued linear layers with phase-equivariant activation functions are used. When viewed from a fixed global frame, all policies learned by this architecture are strictly invariant to choice of local frames. This architecture is shown to increase the data efficiency, tracking performance, and generalization of learned control when compared to a real-valued baseline on an imitation learning flocking task.