Research being conducted by the U.S. Army Combat Capabilities Development Command (DEVCOM) is focused on a new machine learning approach that could improve radar performance in congested environments. Researchers from DEVCOM, Army Research Laboratory, and Virginia Tech have developed an automatic way for radars to operate in congested and limited-spectrum environments created by commercial 4G LTE and future 5G communications systems. The researchers claim they examined how future Department of Defense radar systems will share the spectrum with commercial communications systems. The team used machine learning to learn the behavior of ever-changing interference in the spectrum and find clean spectrum to maximize the radar performance. Once clean spectrum is identified, waveforms can be modified to best fit into the spectrum.

In this paper, we formalize and study the Moving Agents in Formation (MAiF) problem, that combines the tasks of finding short collision-free paths for multiple agents and keeping them in close adherence to a desired formation. Previous work includes controller-based algorithms, swarm-based algorithms, and potential-field-based algorithms. They usually focus on only one or the other of these tasks, solve the problem greedily without systematic search, and thus generate costly solutions or even fail to find solutions in congested environment. In this paper, we develop a two-phase search algorithm, called SWARM-MAPF, whose first phase is inspired by swarm-based algorithms (in open regions) and whose second phase is inspired by multi-agent path-finding (MAPF) algorithms (in congested regions). In the first phase, SWARM-MAPF selects a leader among the agents and finds a path for it that is sufficiently far away from the obstacles so that the other agents can preserve the desired formation around it. It also identifies the critical segments of the leader's path where the other agents cannot preserve the desired formation and the refinement of which has thus to be delegated to the second phase. In the second phase, SWARM-MAPF refines these segments. Theoretically, we prove that SWARM-MAPF is complete. Empirically, we show that SWARM-MAPF scales well and is able to find close-to-optimal solutions.