A drone swarm intelligence-inspired approach to mapping offshore oil spill boundaries is under development at University at Buffalo, State University of New York. A five-drone swarm that can map a nearly one-kilometer-wide spill in nine minutes has been simulated and optimized (see video).

The researchers devised a method for unmanned aerial vehicles (UAVs) to quickly record whether they are over water, oil, or the edge of the spill. The UAVs assume that the space around the oil they have spotted is also oil, although that is recorded as less than certain. Information is shared with the other drones in the swarm, as opposed to sharing actual images or video, which would require too much bandwidth.

Each drone moves from point to point over the spill without duplicating coverage of other UAVs in the swarm. With five drones making observations every five seconds, the size of the spill can be determined quickly. As the drones return to their boat base in response to battery depletion, replacement UAVs which have acquired up-to-date mapping data are activated.

The scheme uses off-the-shelf drones that cost under $1,000, Raspberry Pi computers, simple drone-mountable camera systems, and specially developed software.

Mapping forest fires or other natural disasters are other potential applications for swarming drones.