Current Search:  Unmanned Systems (x)

View All Items

  • CSV Spreadsheet
(1 - 4 of 4)
COALITION FORMATION IN MULTI-AGENT UAV SYSTEMS
Title
COALITION FORMATION IN MULTI-AGENT UAV SYSTEMS.
Creator
DeJong, Paul, Boloni, Ladislau, University of Central Florida
Abstract / Description
Coalitions are collections of agents that join together to solve a common problem that either cannot be solved individually or can be solved more efficiently as a group. Each individual agent has capabilities that can benefit the group when working together as a coalition. Typically, individual capabilities are joined together in an additive way when forming a coalition. This work will introduce a new operator that is used when combining capabilities, and suggest that the behavior of the...
Show moreCoalitions are collections of agents that join together to solve a common problem that either cannot be solved individually or can be solved more efficiently as a group. Each individual agent has capabilities that can benefit the group when working together as a coalition. Typically, individual capabilities are joined together in an additive way when forming a coalition. This work will introduce a new operator that is used when combining capabilities, and suggest that the behavior of the operator is contextual, depending on the nature of the capability itself. This work considers six different capabilities of Unmanned Air Vehicles (UAV) and determines the nature of the new operator in the context of each capability as coalitions (squadrons) of UAVs are formed. Coalitions are formed using three different search algorithms, both with and without heuristics: Depth-First, Depth-First Iterative Deepening, and Genetic Algorithm (GA). The effectiveness of each algorithm is evaluated. Multi agent-based UAV simulation software was developed and used to test the ideas presented. In addition to coalition formation, the software aims to address additional multi-agent issues such as agent identity, mutability, and communication as applied to UAV systems, in a realistic simulated environment. Social potential fields provide a means of modeling a clustering attractive force at the same time as a collision-avoiding repulsive force, and are used by the simulation to maintain aircraft position relative to other UAVs.
Show less
Date Issued
2005
Identifier
CFE0000394, ucf:46332
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0000394
An SoS Conceptual Model, LVC Simulation Framework, and a Prototypical Implementation of Unmanned System Interventions for Nuclear Power Plant Disaster Preparedness, Response, and Mitigation
Title
An SoS Conceptual Model, LVC Simulation Framework, and a Prototypical Implementation of Unmanned System Interventions for Nuclear Power Plant Disaster Preparedness, Response, and Mitigation.
Creator
Davis, Matthew, Proctor, Michael, O'Neal, Thomas, Reilly, Charles, Sulfredge, C., Smith, Roger, University of Central Florida
Abstract / Description
Nuclear power plant disasters can have severe and far-reaching consequences, thus emergency managers and first responders from utility owners to the DoD must be prepared to respond to and mitigate effects protecting the public and environment from further damage. Rapidly emerging unmanned systems promise significant improvement in response and mitigation of nuclear disasters. Models and simulations (M(&)S) may play a significant role in improving readiness and reducing risks through its use...
Show moreNuclear power plant disasters can have severe and far-reaching consequences, thus emergency managers and first responders from utility owners to the DoD must be prepared to respond to and mitigate effects protecting the public and environment from further damage. Rapidly emerging unmanned systems promise significant improvement in response and mitigation of nuclear disasters. Models and simulations (M(&)S) may play a significant role in improving readiness and reducing risks through its use in planning, analysis, preparation training, and mitigation rehearsal for a wide spectrum of derivate scenarios. Legacy nuclear reactor M(&)S lack interoperability between themselves and avatar or agent-based simulations of emergent unmanned systems. Bridging the gap between past and the evolving future, we propose a conceptual model (CM) using a System of System (SoS) approach, a simulation federation framework capable of supporting concurrent and interoperating live, virtual and constructive simulation (LVC), and demonstrate a prototypical implementation of an unmanned system intervention for nuclear power plant disaster using the constructive simulation component. The SoS CM, LVC simulation framework, and prototypical implementation are generalizable to other preparedness, response, and mitigation scenarios. The SoS CM broadens the current stovepipe reactor-based simulations to a system-of-system perspective. The framework enables distributed interoperating simulations with a network of legacy and emergent avatar and agent simulations. The unmanned system implementation demonstrates feasibility of the SoS CM and LVC framework through replication of selective Fukushima events. Further, the system-of-systems approach advances life cycle stages including concept exploration, system design, engineering, training, and mission rehearsal. Live, virtual, and constructive component subsystems of the CM are described along with an explanation of input/output requirements. Finally, applications to analysis and training, an evaluation of the SoS CM based on recently proposed criteria found in the literature, and suggestions for future research are discussed.
Show less
Date Issued
2017
Identifier
CFE0006732, ucf:51879
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0006732
EFFECT OF OPERATOR CONTROL CONFIGURATION ON UNMANNED AERIAL SYSTEM TRAINABILITY
Title
EFFECT OF OPERATOR CONTROL CONFIGURATION ON UNMANNED AERIAL SYSTEM TRAINABILITY.
Creator
Neumann, John, Kincaid, Peter, University of Central Florida
Abstract / Description
Unmanned aerial systems (UAS) carry no pilot on board, yet they still require live operators to handle critical functions such as mission planning and execution. Humans also interpret the sensor information provided by these platforms. This applies to all classes of unmanned aerial vehicles (UAV's), including the smaller portable systems used for gathering real-time reconnaissance during military operations in urban terrain. The need to quickly and reliably train soldiers to control small...
Show moreUnmanned aerial systems (UAS) carry no pilot on board, yet they still require live operators to handle critical functions such as mission planning and execution. Humans also interpret the sensor information provided by these platforms. This applies to all classes of unmanned aerial vehicles (UAV's), including the smaller portable systems used for gathering real-time reconnaissance during military operations in urban terrain. The need to quickly and reliably train soldiers to control small UAS operations demands that the human-system interface be intuitive and easy to master. In this study, participants completed a series of tests of spatial ability and were then trained (in simulation) to teleoperate a micro-unmanned aerial vehicle equipped with forward and downward fixed cameras. Three aspects of the human-system interface were manipulated to assess the effects on manual control mastery and target detection. One factor was the input device. Participants used either a mouse or a specially programmed game controller (similar to that used with the Sony™ Playstation 2 video game console). A second factor was the nature of the flight control displays as either continuous or discrete (analog v. digital). The third factor involved the presentation of sensor imagery. The display could either provide streaming video from one camera at a time, or present the imagery from both cameras simultaneously in separate windows. The primary dependent variables included: 1) time to complete assigned missions, 2) number of collisions, 3) number of targets detected, and 4) operator workload. In general, operator performance was better with the game controller than with the mouse, but significant improvement in time to complete occurred over repeated trials regardless of the device used. Time to complete missions was significantly faster with the game controller, and operators also detected more targets without any significant differences in workload compared to mouse users. Workload on repeated trials decreased with practice, and spatial ability was a significant covariate of workload. Lower spatial ability associated with higher workload scores. In addition, demographic data including computer usage and video gaming experience were collected and analyzed, and correlated with performance. Higher video gaming experience was also associated with lower workload.
Show less
Date Issued
2006
Identifier
CFE0001496, ucf:47080
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0001496
Instructional Strategies for Scenario-Based Training of Human Behavior Cue Analysis with Robot-Aided Intelligence, Surveillance, Reconnaissance
Title
Instructional Strategies for Scenario-Based Training of Human Behavior Cue Analysis with Robot-Aided Intelligence, Surveillance, Reconnaissance.
Creator
Salcedo, Julie, Lackey, Stephanie, Reinerman, Lauren, Barber, Daniel, Kincaid, John, Matthews, Gerald, University of Central Florida
Abstract / Description
The U.S. Army desires to improve safety during Intelligence, Surveillance, Reconnaissance (ISR) operations by removing Warfighters from direct line-of-fire by enhancing ISR operational capabilities with unmanned systems, also known as Robot-Aided ISR (RAISR) (DOD, 2013). Additionally, RAISR presents an opportunity to fulfill ISR capability requirements of modern combat environments including: detection of High-Value Individuals (HVI) from safer distances, identification of baseline behavior,...
Show moreThe U.S. Army desires to improve safety during Intelligence, Surveillance, Reconnaissance (ISR) operations by removing Warfighters from direct line-of-fire by enhancing ISR operational capabilities with unmanned systems, also known as Robot-Aided ISR (RAISR) (DOD, 2013). Additionally, RAISR presents an opportunity to fulfill ISR capability requirements of modern combat environments including: detection of High-Value Individuals (HVI) from safer distances, identification of baseline behavior, and interpretation of adversarial intent (U.S. Army, 2008). Along with the demand and projected acquisition of RAISR technology, there is the added need to design training requirements for system operation and task execution instruction. While documentation identifying specific training standards and objectives for ISR tasks utilizing unmanned systems is limited (DOD, 2013), simulation-based training has been identified as a critical training medium for RAISR (U.S. Army, 2008). ISR analysts will primarily conduct RAISR tasks via Indirect Vision Displays (IVD) which transition well into multimodal simulations (Salcedo, Lackey, (&) Maraj, 2014). However, simulation alone may not fulfill the complex training needs of RAISR tasks, therefore, incorporating instructional support may improve the effectiveness of training (Oser, Gualtieri, Cannon-Bowers, (&) Salas, 1999). One method to accomplish this is to utilize a Scenario-Based Training (SBT) framework enhanced with instructional strategies to target specific training objectives.The purpose for the present experiment was to assess the effectiveness of SBT enhanced with selected instructional strategies for a PC-based RAISR training simulation. The specific task type was the identification of HVIs within a group through behavior cue analysis. The instructional strategies assessed in this experiment, Highlighting and Massed Exposure, have shown to improve attentional weighting, visual search, and pattern recognition skills, which are critical for successful behavior cue analysis. Training effectiveness was evaluated by analyzing the impact of the instructional strategies on performance outcomes, including detection accuracy, classification accuracy, and median response time, and perceptions of the level of engagement, immersion, and presence during training exercises. Performance results revealed that the Massed Exposure strategy produced significantly faster response times for one subtle and one familiar target behavior cue. Perception results indicated that Highlighting was the least challenging instructional strategy and the Control offered the preferred level of challenge. The relationships between performance and perception measures revealed that higher levels of engagement, immersion, and presence were associated with better performance in the Control, but this trend did not always hold for Massed Exposure and Highlighting. Furthermore, presence emerged as the primary predictor of performance for select target behavior cues in the Control and Massed Exposure conditions, while immersion and engagement predicted performance of select cues in the Highlighting condition. The findings of the present experiment point to the potential benefit of SBT instructional strategies to improve effectiveness of simulation-based training for behavior cue analysis during RAISR operations. Specifically, the findings suggest that the Massed Exposure strategy has the potential to improve response time when detecting both familiar and novel targets. The results also highlight directions for future research to investigate methods to alter instructional strategy design and delivery in order to improve trainee perceptions of the instruction.
Show less
Date Issued
2014
Identifier
CFE0005705, ucf:50151
Format
Document (PDF)
PURL
http://purl.flvc.org/ucf/fd/CFE0005705