Heterogenous Swarms for Multimodal Operations
This talk will focus on swarm behavior development at the United States Military Academy, West Point, New York. In 2016, the Defense Advanced Research Projects Agency (DARPA) sponsored the Service Academy Swarm Challenge consisting of a 25 vs 25 live-fly swarm in aerial combat using virtual weapons systems between the three service academies (Army, Navy, and Air Force). In 2017, the swarm infrastructure was re-purposed for a post nuclear detonation forensics mission to collect radiation data and build corresponding heat maps for ground collection teams. Currently, object classification capabilities and associated reactive swarm behaviors are being developed in a decentralized swarm of autonomous unmanned aerial vehicles. These capabilities will be demonstrated live using a fully functional UAV swarm. Each UAV possesses a separate capability to recognize objects using the You Only Look Once (YOLO) neural network model. The UAVs communicate and share data through a swarm software architecture using an adhoc mesh wireless network. When one UAV recognizes a particular object of interest, the entire swarm reacts with a pre-programmed behavior. This talk will highlight past and current swarm research at West Point.