Learning to Identify Graphs from Node Trajectories in Multi-Robot Networks
This addresses the challenge of discovering interactions in networks without prior knowledge, which is crucial for applications like multi-robot formation and flocking, though it appears incremental as it builds on existing methods with a novel hybrid approach.
The paper tackles the graph identification problem in multi-robot networks by proposing a learning-based approach that combines a convex optimization program with a self-attention encoder, enabling identification of graph topologies for unseen network configurations with new numbers of nodes, connectivity, or state trajectories.
The graph identification problem consists of discovering the interactions among nodes in a network given their state/feature trajectories. This problem is challenging because the behavior of a node is coupled to all the other nodes by the unknown interaction model. Besides, high-dimensional and nonlinear state trajectories make it difficult to identify if two nodes are connected. Current solutions rely on prior knowledge of the graph topology and the dynamic behavior of the nodes, and hence, have poor generalization to other network configurations. To address these issues, we propose a novel learning-based approach that combines (i) a strongly convex program that efficiently uncovers graph topologies with global convergence guarantees and (ii) a self-attention encoder that learns to embed the original state trajectories into a feature space and predicts appropriate regularizers for the optimization program. In contrast to other works, our approach can identify the graph topology of unseen networks with new configurations in terms of number of nodes, connectivity or state trajectories. We demonstrate the effectiveness of our approach in identifying graphs in multi-robot formation and flocking tasks.