Key points are not available for this paper at this time.
Safety-critical autonomous systems are becoming more powerful and more integrated to enable higher-level functionality. Modern multi-core SOCs are often the computing backbone in such systems for which safety and associated certification tasks are one of the key challenges, which can become more costly and difficult to achieve. Hence, modeling and assessment of these systems can be a formidable task. In addition, Artificial Intelligence (AI) is already being deployed in safety critical autonomous systems and Machine Learning (ML) enables the achievement of tasks in a cost-effective way.Compliance to Soft Error Rate (SER) requirements is an important element to be successful in these markets. When considering SER performance for functional safety, we need to focus on accurately modeling vulnerability factors for transient analysis based on AI and Deep Learning workloads. We also need to consider the reliability implications due to long mission times leading to high utilization factors for autonomous transport. The reliability risks due to these new use cases also need to be comprehended for modeling and mitigation and would directly impact the safety analysis for these systems. Finally, the need for telemetry for reliability, including capabilities for anomaly detection and prognostics techniques to minimize field failures is of paramount importance.
Athavale et al. (Mon,) studied this question.