The field of autonomous vehicles is witnessing significant advancements in safety and reliability. Researchers are focusing on developing innovative methods to detect and mitigate potential failures in sensors and systems, which is crucial for ensuring the smooth operation of autonomous vehicles. One of the key directions in this field is the development of anomaly detection systems that can identify potential issues in real-time, enabling prompt corrective actions. These systems leverage machine learning and deep learning techniques to analyze sensor data and detect patterns that may indicate a malfunction. Furthermore, researchers are exploring ways to improve the resilience of autonomous vehicles to attacks on their sensors and systems, which is essential for maintaining their safety and reliability. Noteworthy papers in this area include: MARS, which introduces a model-based anomaly detection and recovery system for unmanned aerial vehicles. RADD, which presents an integrated approach to anomaly detection in drones that combines rule mining and unsupervised learning. RouthSearch, which determines valid ranges for PID parameters in flight control programs to prevent misconfiguration.