Real-Time Assessment of Bystander Situation Awareness in Drone-Assisted First Aid

2025-10-03

AI Summary

Real-time situational awareness (SA) assessment for untrained bystanders during opioid overdose events (OOEs) remains challenging under drone-assisted emergency response. Method: We introduce DANDSD—the first drone-assisted naloxone delivery simulation dataset—and propose a graph embedding–Transformer hybrid model that jointly encodes geometric, kinematic, and interaction graph features to dynamically model visual perception and comprehension cues. Contribution/Results: The framework enables adaptive drone guidance and significantly improves real-time SA assessment accuracy: it achieves 9% higher mean over frames (MoF) and 5% higher intersection-over-union (IoU) than the FINCH baseline on temporal segment segmentation. This work pioneers the integration of quantitative SA evaluation into the drone-enabled prehospital intervention loop, establishing a deployable technical paradigm for ultra-timely out-of-hospital care.

Technology Category

Search and Optimization: Sampling/Simulation-based SearchIntelligent Robots: Multimodal Perception & Sensor FusionPlanning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphsSearch and Retrieval-Augmented AI: Web evaluation methodologies and metricsSemantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Rapid naloxone delivery via drones offers a promising solution for responding to opioid overdose emergencies (OOEs), by extending lifesaving interventions to medically untrained bystanders before emergency medical services (EMS) arrive. Recognizing the critical role of bystander situational awareness (SA) in human-autonomy teaming (HAT), we address a key research gap in real-time SA assessment by introducing the Drone-Assisted Naloxone Delivery Simulation Dataset (DANDSD). This pioneering dataset captures HAT during simulated OOEs, where college students without medical training act as bystanders tasked with administering intranasal naloxone to a mock overdose victim. Leveraging this dataset, we propose a video-based real-time SA assessment framework that utilizes graph embeddings and transformer models to assess bystander SA in real time. Our approach integrates visual perception and comprehension cues--such as geometric, kinematic, and interaction graph features--and achieves high-performance SA prediction. It also demonstrates strong temporal segmentation accuracy, outperforming the FINCH baseline by 9% in Mean over Frames (MoF) and 5% in Intersection over Union (IoU). This work supports the development of adaptive drone systems capable of guiding bystanders effectively, ultimately improving emergency response outcomes and saving lives.

Problem

• Assessing bystander situational awareness during drone-assisted opioid overdose emergencies
• Developing real-time video-based framework for human-autonomy teaming evaluation
• Creating adaptive drone systems to guide untrained bystanders in first aid

Innovation

• Video-based real-time SA assessment framework
• Utilizes graph embeddings and transformer models
• Integrates geometric, kinematic, and interaction features