The public repoTting burden for this collection of information is estinuted to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, searching existing data sources, gathering and maintaining the data needed, artd completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of infonnalion, including suggestions for reducing this burden,
AFRLA^ACA
SPONSORING/MONITORING AGENCY REPORT NUMBER(S)AFRL-VA-WP-TP-2003-304
DISTRIBUTION/AVAILABILITY STATEMENTApproved for public release; distribution is unlimited.
SUPPLEMENTARY NOTESTo be presented at the Conference on Decision and Control, Maui, HI, 9-12 Dec 03.© 2003 IEEE. This work is copyrighted. This work, resulting from Department of Air Force contract number F33615-01-C-3150, has been submitted for publication in the Proceedings of the 2003 IEEE Conference on Decision and Control. If published, IEEE may assert copyright. If so, the United States has for itself and others acting on its behalf an unlimited, nonexclusive, irrevocable, paid-up royalty-free worldwide license to use for its purposes.
ABSTRACT (Maximum 200 Words)A software architecture is presented, which introduces several agents which focus on different aspects of path planning for multiple autonomous unmanned aerial vehicles (UAV's) that are searching an uncertain and threatening environment for targets. One agent models threats in the environment. Another develops a model of the environment that allows targets to be defined by individual probability distribution. Lastly, an agent is presented that utilizes the information from the other agents to generate a near optimal path plan using a Dynamic Programming algorithm. Abstract A software architecture is presented, which introduces several agents which focus on different aspects of path planning for multiple autonomous unmanned aerial vehicles (UAV's) that are searching an uncertain and threatening environment for targets. One agent models threats in the environment. Another develops a model of the environment that allows targets to be defined by individual probability distribution. Lastly, an agent is presented that utilizes the information from the other agents to generate a near optimal path plan using a Dynamic Programming algorithm.