Learning Connectivity-Maximizing Network Configurations
This addresses the scalability issue for online applications in multi-robot systems, though it is incremental as it builds on existing optimization methods.
The paper tackled the problem of optimizing algebraic connectivity for robot teams by proposing a supervised learning approach with a CNN to place communication agents, achieving configurations over an order of magnitude faster than an optimization-based scheme for 10-20 agents.
In this letter we propose a data-driven approach to optimizing the algebraic connectivity of a team of robots. While a considerable amount of research has been devoted to this problem, we lack a method that scales in a manner suitable for online applications for more than a handful of agents. To that end, we propose a supervised learning approach with a convolutional neural network (CNN) that learns to place communication agents from an expert that uses an optimization-based strategy. We demonstrate the performance of our CNN on canonical line and ring topologies, 105k randomly generated test cases, and larger teams not seen during training. We also show how our system can be applied to dynamic robot teams through a Unity-based simulation. After training, our system produces connected configurations over an order of magnitude faster than the optimization-based scheme for teams of 10-20 agents.