A Situational Assessment Module for CCAM Applications

The rapid growth of connectivity and automation has led to the rise of Connected Cooperative Automated Mobility (CCAM), which aims to enhance transportation systems through integrated networks of vehicles, pedestrians, infrastructure, and cloud services. However, increased connectivity also introduces new cyber threats. This study focuses on improving the sit-uational awareness of AI-based systems to detect anomalies, including those caused by cyber-attacks. It proposes a Situational Assessment Module (SAM) for CCAM ecosystems, which uses AI to compare data from vehicle sensors and Roadside Units (RSUs) with internal vehicle messages, detecting anomalies and assessing risk levels. Four AI models are developed to detect specific anomalies, including GNSS loss-spoofing, RSU-vehicle mismatches, lateral and longitudinal motion anomalies. For risk assessment, a rule-based system interprets the severity and probability of anomalies to guide the vehicle's safe operation.