Reliability Analysis of Artificial Intelligence Systems Using Recurrent Events Data from Autonomous Vehicles
This work provides a method for assessing the reliability of AI systems, particularly for autonomous vehicles, by leveraging publicly available recurrent event data, which is crucial for safe and effective deployment.
This paper addresses the challenge of assessing AI system reliability due to limited data by utilizing publicly available recurrent disengagement event data from autonomous vehicle (AV) road tests. It proposes a statistical framework, including both parametric and a new nonparametric monotonic spline model, to analyze this data and infer the reliability of AI systems in AVs.
Artificial intelligence (AI) systems have become increasingly common and the trend will continue. Examples of AI systems include autonomous vehicles (AV), computer vision, natural language processing, and AI medical experts. To allow for safe and effective deployment of AI systems, the reliability of such systems needs to be assessed. Traditionally, reliability assessment is based on reliability test data and the subsequent statistical modeling and analysis. The availability of reliability data for AI systems, however, is limited because such data are typically sensitive and proprietary. The California Department of Motor Vehicles (DMV) oversees and regulates an AV testing program, in which many AV manufacturers are conducting AV road tests. Manufacturers participating in the program are required to report recurrent disengagement events to California DMV. This information is being made available to the public. In this paper, we use recurrent disengagement events as a representation of the reliability of the AI system in AV, and propose a statistical framework for modeling and analyzing the recurrent events data from AV driving tests. We use traditional parametric models in software reliability and propose a new nonparametric model based on monotonic splines to describe the event process. We develop inference procedures for selecting the best models, quantifying uncertainty, and testing heterogeneity in the event process. We then analyze the recurrent events data from four AV manufacturers, and make inferences on the reliability of the AI systems in AV. We also describe how the proposed analysis can be applied to assess the reliability of other AI systems.