Heterogeneous Sensor Networks: A Bio-Inspired Overlay Architecture

A team consisting of Teledyne Scientific Company, the University of California at Santa Barbara (UCSB) and the Army Research Laboratory (ARL) is developing technologies in support of automated data exfiltration from heterogeneous battlefield sensor networks as part of a US Army contract with the Institute for Collaborative Biotechnologies (ICB) at UCSB. The objective of the program is to design, develop and test data gathering strategies, feature and information fusion concepts from unattended ground sensor networks in support of situation awareness for dismounts. Networks of heterogeneous sensors are typically deployed in sparse configurations over wide areas (one sensor per square kilometer) in order to detect infiltration and adversarial events of interest to coalition forces. The sensors within a network cannot communicate with each other and consequently require overhead assets to automatically extract and process data in a timely fashion. Unmanned air vehicles (UAV) provide an effective means to autonomously collect data from a sparse network of unattended ground sensors (UGSs) that cannot communicate with each other due to their sparse distribution. In addition to providing a communication infrastructure and a mechanism for implicit synchronization of sensors, UAVs can also be used to reduce the system reaction time by generating autonomous collection routes that are data-driven. Bio-inspired techniques for search provide a novel strategy to detect, capture and fuse data across heterogeneous sensor networks. A fast and accurate method has been developed to localize an event on the ground by fusing data from a sparse number of UGSs involving the use of a bio-inspired algorithm based on chemotaxis or the motion of bacteria seeking nutrients in their environment. A unique acoustic event classification algorithm was also developed based on using swarm optimization to classify events. Very high classification accuracies were achieved against ARL field data using the swarm optimization method. The system was initially implemented and successfully tested using a high level simulation environment with a flight simulator to emulate a UAV collector. The high level simulation was extended by replacing the flight simulator with a real UAV and moving the architecture to the field. Approved for Public Release Distribution is Unlimited