Heterogeneous Sensor Networks: A Bio-Inspired Overlay Architecture

摘要

Sensor networks need to provide timely and accurate information about events on the ground to the dismounts and upper echelons in support of the mission and operations. Current unattended ground sensors (UGS) can provide accurate (local) temporal detection of events, but do not provide adequate performance in identifying objects from multiple sensors via the fusion of disparate sensor data. The Army needs timely dissemination of relevant information in the form of classification of terrestrial events, occurrence times, their trajectories and direction of movement of adversarial activities. The Army currently employs heterogeneous UGSs using a sparse deployment to maximize coverage, minimize pilferage and to monitor terrain bottlenecks. The Army Research Lab (ARL) is moving towards an architecture (Family of UGSs) that will standardize communications (e.g. Blue Radio) and this will help to mitigate the heterogeneous UGS network problem. The Institute for Collaborative Biotechnologies (ICB) program is developing and will demonstrate a new system of bioinspired software algorithms for autonomous operations that will leverage proven research to monitor heterogeneous UGS networks from extended ranges, that will collect data in a timely fashion, that will collaboratively control the motion of a sparse network of collectors (e.g. UAV's) using bio-inspired strategies, that will localize and synchronize communications, that will accurately detect and localize field events and will fuse and classify sensed data from UGSs using methods from Evolutionary Computing. The program will also provide both laboratory and field demonstrations of these capabilities supported through ARL by leveraging available resources.