Date of Graduation
5-2008
Document Type
Thesis
Degree Name
Bachelor of Science in Computer Engineering
Degree Level
Undergraduate
Department
Computer Science and Computer Engineering
Advisor/Mentor
Di, Jia
Committee Member/Reader
Thompson, Craig W.
Committee Member/Second Reader
Parkerson, Patrick
Abstract
Traditional automatic target recognition (ATR) is performed by unmanned aerial vehicles (UAVs) depending on a central control tower to provide the high level organization of the system. The UAVs fly through a region of interest to identify targets and relay all communication through a central control tower. The centralized approach to ATR has limited fault-tolerance, scalability with regards to the number of UAVs, and susceptibility to malicious attacks on the central tower [2]. A swarm-driven alternative [1] is extended with a communication control scheme to address fault-tolerance and scalability while utilizing the higher onboard processing power now available for UAVs [2]. The purpose of this paper is to compare the organization systems, centrally controlled versus distributed swarm, and extend on swarm research in the area of communication to aid in the comparison. A swarm communication algorithm is proposed and simulated during search and destroy missions in the MultiUAV2 simulation framework. Highlighted algorithm properties will be time to message completion, bandwidth costs of each configuration, scalability, and quality of service.
Citation
White, K. (2008). MultiUAV2 Agent Swarming for Distributed ATR Simulation. Computer Science and Computer Engineering Undergraduate Honors Theses Retrieved from https://scholarworks.uark.edu/csceuht/9