[论文解读] Research Directions for Developing and Operating Artificial Intelligence Models in Trustworthy Autonomous Systems.

Silverio Martínez‐Fernández, Xavier Franch+3 more|arXiv (Cornell University)|Mar 11, 2020

Ethics and Social Impacts of AI参考文献 4被引用 8

一句话总结

本文提出了一套全面的DevOps框架，用于统一自主系统（ASs）中可信AI模型的开发与运维，实现在动态、恶劣条件下的持续演化与信任监控。核心贡献是一项五方面研究议程，涵盖可信度评分、敏捷AI开发、运维反馈收集、跨分布式系统的无缝部署，以及统一的AI生命周期管理。

ABSTRACT

Context: Autonomous Systems (ASs) are becoming increasingly pervasive in today's society. One reason lies in the emergence of sophisticated Artificial Intelligence (AI) solutions that boost the ability of ASs to self-adapt in increasingly complex and dynamic environments. Companies dealing with AI models in ASs face several problems, such as users' lack of trust in adverse or unknown conditions, and gaps between systems engineering and AI model development and evolution in a continuously changing operational environment. Objective: This vision paper aims to close the gap between the development and operation of trustworthy AI-based ASs by defining a process that coordinates both activities. Method: We synthesize the main challenges of AI-based ASs in industrial settings. To overcome such challenges, we propose a novel, holistic DevOps approach and reflect on the research efforts required to put it into practice. Results: The approach sets up five critical research directions: (a) a trustworthiness score to monitor operational AI-based ASs and identify self-adaptation needs in critical situations; (b) an integrated agile process for the development and continuous evolution of AI models; (c) an infrastructure for gathering key feedback required to address the trustworthiness of AI models at operation time; (d) continuous and seamless deployment of different context-specific instances of AI models in a distributed setting of ASs; and (e) a holistic and effective DevOps-based lifecycle for AI-based ASs. Conclusions: An approach supporting the continuous delivery of evolving AI models and their operation in ASs under adverse conditions would support companies in increasing users' trust in their products.

研究动机与目标

• 应对在不利或未知运行条件下，用户对基于AI的自主系统（ASs）日益增长的不信任问题。
• 弥合系统工程与AI模型开发/演化之间在持续变化环境中的差距。
• 在维持可信度的前提下，实现自主系统中演化AI模型的持续交付与运维。
• 建立一种协调流程，统一AI模型开发与运行时操作，以提升系统可靠性。
• 为工业级自主系统部署中可信、自适应且可扩展的AI奠定研究驱动的基础。

提出的方法

• 引入可信度评分，实时监控AI模型行为，并在关键情境下检测自适应需求。
• 设计一种与系统工程实践对齐的集成敏捷流程，支持AI模型的持续开发与演化。
• 实施基础设施，用于收集与分析关键运维反馈，以评估和提升AI模型的可信度。
• 实现跨分布式自主系统的上下文特定AI模型实例的持续无缝部署。
• 建立基于全面DevOps的生命周期，统一AI模型的开发、部署、监控与自适应。
• 结合系统工程原则与AI生命周期管理，支持动态、自适应且可信的自主系统运行。

实验结果

研究问题

• RQ1 如何有效定义并监控可信度评分，以检测基于AI的自主系统中的关键运行偏差？
• RQ2 在自主系统中，为支持AI模型与系统工程实践对齐的持续演化，需要哪些敏捷开发流程？
• RQ3 需要何种反馈基础设施，以实现AI模型可信度的运行时评估与改进？
• RQ4 如何实现跨分布式自主系统的不同上下文特定AI模型实例的持续无缝部署？
• RQ5 何种全面的DevOps生命周期模型能够整合AI开发与运维管理，以实现可信自主系统？

主要发现

• 可信度评分可实现对AI模型行为的实时监控，并在关键阈值被突破时触发自适应机制。
• 集成的AI模型开发敏捷流程支持在动态环境中持续演化，并与系统工程实践保持对齐。
• 专用的反馈基础设施对于收集可支持可信度评估与模型改进的运行数据至关重要。
• 通过统一的DevOps流水线，可实现跨分布式自主系统的上下文特定AI模型实例的无缝部署。
• 基于全面DevOps的AI自主系统生命周期，可在不利条件下实现持续交付、监控与自适应。
• 所提出的框架通过确保AI模型在复杂运行场景中保持可靠、可解释与可适应，增强了用户信任。