ORCID Number
https://orcid.org/0000-0001-7236-5162
Date of Award
Summer 7-2026
Access Type
Dissertation - Open Access
Degree Name
Doctor of Philosophy in Electrical Engineering & Computer Science
Department
Electrical, Computer, Software, and Systems Engineering
Committee Chair
Richard S. Stansbury
Committee Chair Email
stansbur@erau.edu
First Committee Member
Joseph R. Keebler
First Committee Member Email
keeblerj@erau.edu
Second Committee Member
Bryan C. Watson
Second Committee Member Email
watsonb3@erau.edu
Third Committee Member
M. Ilhan Akbas
Third Committee Member Email
akbasm@erau.edu
Fourth Committee Member
Niranjan Suri
Fourth Committee Member Email
nsuri@ihmc.org
College Dean
James W. Gregory
Abstract
Modern multi-agent Urban Search and Rescue (USAR) operations heavily rely on mobile geospatial Common Operating Pictures (COPs) to maintain team coordination and Situational Awareness (SA). However, the proliferation of high-frequency sensor telemetry at the tactical edge has introduced a data saturation paradox challenge: while information theoretically drives informed decision-making, unmanaged data surges induce increased operator cognitive overload and alert fatigue on mobile End-User Devices (EUDs), while downstream data-broadcasting models inherently strain edge processing and viewport environments.
To resolve these constraints, this dissertation presents a context-aware Value of Information (VoI) data-management framework integrated directly with a custom, event-driven Android Team Awareness Kit (ATAK) plugin architecture. Designed with structural deployment flexibility, the framework decouples the core rule-based processing engine from the client presentation layer. This allows the system to execute information filtering and prioritization at any node, minimizing data-handling inefficiencies and data model clutter before they reach the operator's viewport. By formalizing expert operational knowledge into a polymorphic, rule-based reasoning engine, the system dynamically maps mission properties, such as spatial boundaries, asset roles, environmental hazards, and causal tracking relationships, into executable, multi-tiered mission profiles. The client interface then leverages an automated, multi-tiered chromatic valuation scale (gray, yellow, orange, and red states) to visually prioritize urgent operational threats based on real-time relevance metrics.
Furthermore, this research addresses the automation trust paradox, where operators routinely reject automated data-filtering mechanisms due to safety-critical accountability, by designing and embedding a structured diagnostic provenance architecture. This layer appends an auditable ledger of rule dependencies directly to individual data entities, enabling operators to tap any map item to instantly review the underlying rationale driving its visualization state.
To evaluate the operational utility of this framework, a high-fidelity distributed simulation environment was developed, linking an asset simulator, a VoI engine, and live ATAK client nodes over single-stream TCP sockets. Human-in-the-loop experiments were conducted across multiple complex USAR scenarios, contrasting an active filtering profile (VoI: ON) against a baseline, unfiltered broadcasting profile (VoI: OFF). To isolate the effect of semantic filtering, advanced motion-based attention-capture mechanics (such as peripheral icon flashing and geometric mid-air de-confliction vectors) were programmatically deactivated during formal testing, restricting user interface interactions exclusively to static chromatic shifts.
The empirical results suggest that the framework achieves statistically significant reductions in local cache memory footprints and data model processing latency. Human-subjects data indicates that by filtering extraneous ambient markers and de-escalating stale threats to a persistent grayed-out state, the framework is associated with reductions in operator cognitive workload and alert fatigue while increasing its situational awareness. The integration of transparent rule tracking successfully mitigated user skepticism, establishing a predictable, explainable decision-support loop that is associated with improvements in situational awareness, decision speed, and team coordination efficiency at the tactical edge without introducing confounding visual interface variables.
Scholarly Commons Citation
Reyes Duran, Daniel, "Improving Urban Search and Rescue Team Coordination Through Adaptive Context Awareness" (2026). Doctoral Dissertations and Master's Theses. 1011.
https://commons.erau.edu/edt/1011
Included in
Artificial Intelligence and Robotics Commons, Cognition and Perception Commons, Cognitive Science Commons, Computer and Systems Architecture Commons, Digital Communications and Networking Commons, Human-Computer Interaction Commons, Human Factors Psychology Commons, Software Engineering Commons, Systems and Communications Commons, Systems Architecture Commons, Systems Science Commons
