Unmanned aerial systems (UAS) have proven themselves to be indispensable in providing intelligence, surveillance, and
reconnaissance (ISR) over the battlefield. Constellations of heterogeneous, multi-purpose UAS are being tasked to
provide ISR in an unpredictable environment. This necessitates the dynamic replanning of critical missions as weather
conditions change, new observation targets are identified, aircraft are lost or equipment malfunctions, and new airspace
restrictions are introduced. We present a method to generate coordinated mission plans for constellations of UAS with
multiple flight goals and potentially competing objectives, and update them on demand as the operational situation
changes. We use a fast evolutionary algorithm-based, multi-objective optimization technique. The updated flight routes
maintain continuity by considering where the ISR assets have already flown and where they still need to go. Both the
initial planning and replanning take into account factors such as area of analysis coverage, restricted operating zones,
maximum control station range, adverse weather effects, military terrain value, and sensor performance. Our results
demonstrate that by constraining the space of potential solutions using an intelligently-formed air maneuver network
with a subset of potential airspace corridors and navigational waypoints, we can ensure global optimization for multiple
objectives considering the situation both before and after the replanning is initiated. We employ sophisticated
visualization techniques using a geographic information system to help the user 'look under the hood" of the algorithms
to understand the effectiveness and viability of the generated ISR mission plans and identify potential gaps in coverage.
The U.S. Air Force is consistently evolving to support current and future operations through the planning and execution
of intelligence, surveillance and reconnaissance (ISR) missions. However, it is a challenge to maintain a precise
awareness of current and emerging ISR capabilities to properly prepare for future conflicts. We present a decisionsupport
tool for acquisition managers to empirically compare ISR capabilities and approaches to employing them,
thereby enabling the DoD to acquire ISR platforms and sensors that provide the greatest return on investment. We have
developed an analysis environment to perform modeling and simulation-based experiments to objectively compare
alternatives. First, the analyst specifies an operational scenario for an area of operations by providing terrain and threat
information; a set of nominated collections; sensor and platform capabilities; and processing, exploitation, and
dissemination (PED) capacities. Next, the analyst selects and configures ISR collection strategies to generate collection
plans. The analyst then defines customizable measures of effectiveness or performance to compute during the
experiment. Finally, the analyst empirically compares the efficacy of each solution and generates concise reports to
document their conclusions, providing traceable evidence for acquisition decisions. Our capability demonstrates the
utility of using a workbench environment for analysts to design and run experiments. Crafting impartial metrics enables
the acquisition manager to focus on evaluating solutions based on specific military needs. Finally, the metric and
collection plan visualizations provide an intuitive understanding of the suitability of particular solutions. This facilitates
a more agile acquisition strategy that handles rapidly changing technology in response to current military needs.
Unmanned aerial vehicles (UAVs) have proven themselves indispensable in providing intelligence, reconnaissance, and
surveillance (ISR). We foresee a future where constellations of multi-purpose UAVs will be tasked to provide ISR in an
unpredictable environment. Automated systems will process imagery and other sensor data gathered by the
constellations to provide continuous situational awareness for the warfighter on the ground. In this paper, we present a
tool that generates coordinated mission plans for constellations of UAVs with multiple goals and objectives. We call this
tool <b>S</b>patially <b>P</b>roduced <b>A</b>irspace <b>R</b>outes from <b>T</b>actical <b>E</b>volved <b>N</b>etworks, or SPARTEN. SPARTEN uses evolutionary
algorithm (EA)-based, multi-objective optimization to generate coordinated sortie routes for constellations of UAVs.
These sortie routes maximize sensor coverage, avoid conflicts between UAVs, minimize the latency of sensor data, and
avoid areas of poor weather to provide valid route solutions. We use an Air Maneuver Network (AMN) based on terrain
reasoning to constrain the solution space. We make two contributions to the field of UAV route planning. We develop a
tool to optimize planning across multiple objectives for constellations of UAVs, and we explore the performance of this
tool on a battlefield scenario.
A common approach to detecting targets in laser radar (LADAR) 3-dimensional x, y and z imagery is to first estimate the ground plane. Once the ground plane is identified, the regions of interest (ROI) are segmented based on height above that plane. The ROIs can then be classifed based on their shape statistics (length, width, height, moments, etc.) In this paper, we present an empirical comparison of three different ground plane estimators. The first estimates the ground plane based on global constraints (a least median squares fit to the entire image). The second two are based on progressively more local constraints: a least median squares fit to each row and column the image, and a local histogram analysis of the re-projected range data. These algorithms are embedded in a larger system that first computes the target height above the ground plane and then recognizes the targets based on properties within the target region. The evaluation is performed using 98 LADAR images containing eight different targets and structured clutter (trees). Performance is measured in terms of percentage of correct detection and false alarm.
Laser vibrometry sensors measure minute surface motion colinear with the sensor's line-of-sight. If the vibrometry sensor has a high enough sampling rate, an accurate estimate of the surface vibration is measured. For vehicles with running engines, an automatic target recognition algorithm can use these measurements to produce identification estimates. The level of identification possible is a function of the distinctness of the vibration signature. This signature is dependent upon many factors, such as engine type and vehicle weight. In this paper, we present results of using data mining techniques to assess the identification potential of vibrometry data. Our technique starts with unlabeled vibrometry measurements taken from a variety of vehicles. Then an unsupervised clustering algorithm is run on features extracted from this data. The final step is to analyze the produced cluters and determine if physical vehicle characteristics can be mapped onto the clusters.