VShreyas Devaraju received his M.S. in Electrical Engineering from San Diego State University (SDSU), San Diego, USA in 2017. He is currently pursuing his Ph.D. in Computational Science jointly at SDSU and University of California, Irvine. His research interests include cross-layer routing and MAC protocols for wireless networks, UAV swarm mobility and communication networks.
Sunil Kumar and Alexander Ihler
Recently, I have been researching into the application of machine learning techniques such as K-means clustering, Support Vector MIn recent years, there has been a surge in the use of inexpensive micro UAV swarms for civilian and military applications such as search and rescue, surveillance and tracking, and as loitering ammunitions. To carry out these operations efficiently, there is a need to develop scalable, decentralized autonomous UAV swarm architectures with high network connectivity. However, the area coverage and the network connectivity requirements exhibit a trade-off. In our work, a connectivity-aware pheromone mobility model is designed for search and rescue operations, which is capable of maintaining connectivity among UAVs in the UAV swarm. We use stigmergy-based digital pheromone maps along with distance-based local connectivity information to autonomously coordinate the UAV movements, in order to improve its map coverage efficiency while maintaining high network connectivity. We also use deep Q-learning to train a connectivity-aware pheromone mobility model that gives the optimal performance in terms of both coverage and connectivity for UAV swarms.