A recent paper by members of the DCIST alliance develops a method for distributed control of large networks of mobile robots with interacting dynamics and sparsely available communications. Their approach is to learn local controllers that require only local information and communications at test time by imitating the policy of centralized controllers using global information at training time. By extending aggregation graph neural networks to time varying signals and time varying network support, they learn a single common local controller which exploits information from distant teammates using only local communication interchanges. The researchers apply this approach to the problem of flocking to demonstrate performance on communication graphs that change as the robots move. They examine how a decreasing communication radius and faster velocities increase the value of multi-hop information.
Task: RA1.C1 Joint Resource Allocation in Perception-Action-Communication Loops
Points of Contact: Alejandro Ribeiro (PI) and Ekaterina Tolstaya
Citation: E. Tolstaya, F. Gama, J. Paulos, G. Pappas, V. Kumar, A. Ribeiro “Learning Decentralized Controllers for Robot Swarms with Graph Neural Networks.” Conference on Robot Learning, October 2019.