Coevolving Collection Plans for UAS Constellations

Stouch, D., Zeidman, E., Callahan, W., and McGraw, K.

Proceedings of the 2011 Genetic and Evolutionary Computation Conference (GECCO), Dublin, Ireland (July 2011).

We are developing a tool called SPARTEN (Spatially Produced Airspace Routes from Tactical Evolved Networks) that generates coordinated mission plans for constellations of unmanned aerial vehicles by allowing the mission planner to specify which objectives are important to them for each mission. Using an evolutionary algorithm-based, multi-objective optimization technique, we consider factors such as area of analysis coverage, restricted operating zones, maximum ground control station range, adverse weather effects, military terrain value, airspace collision avoidance, path linearity, named area of analysis emphasis, and sensor performance. By employing novel visualization techniques using geographic information systems to represent their effectiveness, we help the user “look under the hood” of the algorithms and understand the viability and effectiveness of the mission plans to identify coverage gaps and other inefficiencies. In this paper, we present our overall approach to the application of multi-objective evolutionary algorithms to the air mission planning domain, with a focus on the visualization components.

SPARTEN Collection Plan Metrics

SPARTEN Collection Plan Metrics

For More Information

To learn more or request a copy of a paper (if available), contact D. Stouch.

(Please include your name, address, organization, and the paper reference. Requests without this information will not be honored.)