Situational Awareness
Situational awareness (SA) research focuses on enabling systems, both robotic and AI-based, to understand and respond appropriately to their environment and context. Current research emphasizes developing models that integrate diverse data sources (e.g., camera images, sensor data, language prompts) using techniques like deep learning (including transformer networks and PointNet), rule-based systems, and multimodal fusion to enhance SA in real-time. This work is crucial for improving safety and efficiency in various applications, including autonomous vehicles, human-robot collaboration, and assistive technologies for vulnerable populations.
Papers
Two-Stage Violence Detection Using ViTPose and Classification Models at Smart Airports
İrem Üstek, Jay Desai, Iván López Torrecillas, Sofiane Abadou, Jinjie Wang, Quentin Fever, Sandhya Rani Kasthuri, Yang Xing, Weisi Guo, Antonios Tsourdos
Assessing Drivers' Situation Awareness in Semi-Autonomous Vehicles: ASP based Characterisations of Driving Dynamics for Modelling Scene Interpretation and Projection
Jakob Suchan, Jan-Patrick Osterloh