home   |   meetings   |   newsletter   |   tutorials   |   books   |   awards   |   contact us

Dr. Peter Shea
   Black River Systems Company, Inc., Lakeville, MN

Sensor Tasking using Genetic Algorithms

December 11, 2007 :: 4:30 - 5:30 pm


  Today's battlefield environment contains a large number of sensors, and sensor types, onboard multiple platforms. The set of sensor types includes SAR, EO/IR, GMTI, AMTI, HSI, MSI, and video, and for each sensor type there may be multiple sensing modalities to select from. In an attempt to maximize sensor performance, today's sensors employ either static tasking approaches or require an operator to manually change sensor tasking operations. In a highly dynamic environment this leads to a situation whereby the sensors become less effective as the sensing environments deviates from the assumed conditions.
  Through a Phase I SBIR effort we developed a system architecture and a common tasking approach for solving the sensor tasking problem as applied to a radar and EO/IR sensor mix. Our sensor tasking considers multiple layers within the task hierarchy ranging from the mission level, where tasking focuses on mission requirements, down to where sensor tasking focuses on radar sub-mode and waveform selection. We also developed a genetic algorithm based task scheduling approach and demonstrated the ability to automatically task and schedule sensors in an end-to-end closed loop simulation. In the proof of concept we demonstrated the ability to schedule multiple radar sensors simultaneously. This provides a solid foundation for our future efforts including incorporation of EO/IR and other sensor types. During the second phase of this effort, we have included additional sensor tasking capabilities in terms of repeating tasks, linked tasks, and sensor resource constraints. Additionally, we have focused effort on the development of automatic needs and task generation capabilities.


 Dr. Shea has been solving problems in the area of tracking and data fusion for over 15 years. He received a B.A. in mathematics from Minnesota State University in Moorhead, MN and his M.S. and Ph.D. degree also in mathematics from Colorado State University. His dissertation dealt with an improved solution approach for multidimensional assignment problems that arise in the multi-sensor multi-target tracking applications. After graduation he worked at Lockheed Martin (formerly ORINCON Corporation) in San Diego, CA where he was a key member of the group working on the tracking of ground targets using MTI radars. He has been working at Black River Systems Company in Lakeville, MN for the past 3 years where he continues to work in the area target tracking and sensor management.




 The meeting will be held at the Lockheed Martin Corporation, 3333 Polot Knob Road, in Eagan

Google Map Loading...