Assignment games are a promising framework for autonomous management of a multimodal Tactical Sensing Grid (TSG). They provide theoretical guarantes and exhibit excellent empirical performance in maintaining custody of all observed targets in a scene. However, TSG sub-grid initiation of an assignment game requires multimodal data association between playing nodes (the sub-grid). Playing nodes must achieve consensus on target labels and identities before game play proceeds. Using the locally centralized communication network assumed by an assignment game, we propose the Triple-C distributed method for solving this association problem. The method we propose is suitable for fairly general scenarios, requiring that each node have an intrinsic notion of what constitutes an outlier and what constitutes similarity. At the core of the Triple-C method is a collection of parallelizable assignment games played between two nodes. Triple-C yields theoretical guarantees on output association consistency. We evaluate the performance of the Triple-C method on multiple simulations, showing that it computes associations quickly and accurately, thus enabling a TSG to maintain full situational awareness in a two-vehicle scenario.

Reinforcement learning is a promising candidate methodology for achieving situational awareness across an area of interest by controlling and processing data acquired from a multi-site, multi-modality sensing grid. We previously reported successful detection, tracking, classification, and identification of objects operating within the area of interest monitored by a sensing grid. We combined online kernel least squares policy iteration (an online reinforcement learning method combining dictionary learning with classical Q-learning) with a particle tracker to achieve these results. The work reported here extends these prior results to show that sensor fusion allows our online reinforcement learning methodology to successfully control a multi-modality sensor platform (consisting of a pan/tilt/zoom electro-optical camera, a radar, and passive radio frequency sensor) to maintain persistent surveillance of objects of interest. We evaluate our sensor fusion and online reinforcement learning methodology through Gazebo simulation of a realistic test and experimentation location. Our results demonstrate that policies based on our methodology trained on processed simulated sensor data perform as well as policies trained on known ground truth data. These results also show that the learned policies offer significant generalization ability, with the sensor platform being able to successfully track an observed object well past the observed training period. Moreover, we show that our reinforcement learning methodology shows promising results in dealing with the data association problem. These results further build towards our ultimate goal of achieving automated situational awareness across a heterogeneous sensor grid.

Finding a minimum dominating set is a classic NP-hard problem from graph theory. Given a finite, simple, undirected graph, it seeks a smallest set of vertices with the property that every vertex in the graph is either in or adjacent to at least one member of that set. In recent years, it has found increased application, particularly when used as the basis for classifying nodes of biological networks. Sample networks include those derived from metabolic, noncoding RNA and protein-protein interaction data. Classification schemes employed to date, however, have typically been limited by the need to solve multiple problem instances, which naturally constrains the size of amenable networks. Moreover, analytical methods based on minimum dominating set have thus far generally been limited to static graphs. In this paper, work in progress is described that improves upon these algorithms and applies them to dynamic streaming graphs in order to capture control structures as they evolve over time. Results demonstrate the effectiveness of these techniques at reducing computational overhead. A systematic experimental setup and a description of testbed construction is also provided.

This paper describes a framework combining graph theoretical tools and metrics with machine learning to analyze big geospatial data. By combining multiple methods targeted to different levels of resolution, this approach detects subtle normalcy patterns that would otherwise remain hidden to any single approach. Initial feasibility testing shows the applicability of the proposed methods to data from trip records of New York City taxis.

Contemporary situational awareness problems such as automated normalcy learning for anomaly detection and motion behavior prediction are addressed with biologically-inspired processing, representation, and learning approaches. Issues and challenges are discussed and our responses to them described. Relatively simple neural principles provide considerable power in providing capabilities required to learn models of normal motion behavior and utilize those models to identify unusual behavior or determine the most likely future behavior of objects of interest.

An improved neurobiologically inspired algorithm for situation awareness in the maritime domain is presented, which takes real-time tracking information and learns motion pattern models on-the- fly, enabling the models to adapt well to evolving situations while maintaining high levels of performance. The constantly refined models, resulting from concurrent incremental learning, are used to evaluate the behavior patterns of vessels based on their present motion states. Improvement to the associative learning law for learning temporal associations between vessel events enables conditional probabilities between events to be learned incrementally and locally. This allows weights in the learned model to be interpreted more readily, enabling better location prediction performance. Improvement in prediction performance is achieved by using multiple spatial scales to represent position, enabling the most relevant spatial scale to be used for local vessel behavior. Features and performance of these updates to the learning system using recorded data are described.

Neurobiologically inspired algorithms have been developed to continuously learn behavioral patterns at a variety of conceptual, spatial, and temporal levels. In this paper, we outline our use of these algorithms for situation awareness in the maritime domain. Our algorithms take real-time tracking information and learn motion pattern models on-the-fly, enabling the models to adapt well to evolving situations while maintaining high levels of performance. The constantly refined models, resulting from concurrent incremental learning, are used to evaluate the behavior patterns of vessels based on their present motion states. At the event level, learning provides the capability to detect (and alert) upon anomalous behavior. At a higher (inter-event) level, learning enables predictions, over pre-defined time horizons, to be made about future vessel location. Predictions can also be used to alert on anomalous behavior. Learning is context-specific and occurs at multiple levels: for example, for individual vessels as well as classes of vessels. Features and performance of our learning system using recorded data are described