Anomaly Detection in Cooperative Vehicle Perception Systems under Imperfect Communication
This work addresses safety-critical anomaly detection for autonomous vehicles, but it is incremental as it builds on cooperative perception with a focus on communication robustness.
The paper tackles anomaly detection in autonomous driving by leveraging cooperative perception to share information across vehicles, achieving improved accuracy and robustness under imperfect communication, with empirical results showing outperformance in F1-score and AUC on a new 90,000-trajectory benchmark dataset.
Anomaly detection is a critical requirement for ensuring safety in autonomous driving. In this work, we leverage Cooperative Perception to share information across nearby vehicles, enabling more accurate identification and consensus of anomalous behaviors in complex traffic scenarios. To account for the real-world challenge of imperfect communication, we propose a cooperative-perception-based anomaly detection framework (CPAD), which is a robust architecture that remains effective under communication interruptions, thereby facilitating reliable performance even in low-bandwidth settings. Since no multi-agent anomaly detection dataset exists for vehicle trajectories, we introduce 15,000 different scenarios with a 90,000 trajectories benchmark dataset generated through rule-based vehicle dynamics analysis. Empirical results demonstrate that our approach outperforms standard anomaly classification methods in F1-score, AUC and showcase strong robustness to agent connection interruptions.