SELFY Infrastructure: an Accurate & Trustworthy Model for CCAM

The EU project SELFY aims at a safer, more resilient and cybersecure CCAM ecosystem. To do so, vehicles and infrastructure have to cooperate, especially to build situational awareness and collective perception.

By combining different sources of data, SELFY infrastructure model is designed to get an accurate and trustworthy understanding of its environment. To perceive local environment, SELFY infrastructure model relies on different types of sensors (e.g. cameras, lidars and radars) to improve the accuracy of the situational awareness. Each type of sensor has its own advantages, and the project Sensor Fusion & Anomaly Detection (SFAD) tool benefits from the advantages of each sensor when fusing results. 

SELFY has a strong focus on security and trustworthiness. What if a camera or a lidar is tampered with or hacked? Such issues are addressed by another key component of SELFY infrastructure model: the Threat Evaluation Tool (TET), which gathers data from SFAD and searches for suspicious patterns.

SELFY infrastructure model exchanges messages with other V2X agents, to check the consistency between their and the infrastructure own perception. This situational awareness also benefits V2X agents, increasing their own perception, and this designs allows to identify emitters of inconsistent V2X messages, either due to malfunctions or attacks.

Source: The original article is published here