论文标题
随机游戏中未经验证的控制器（基于AI）
Sandboxing (AI-based) Unverified Controllers in Stochastic Games: An Abstraction-based Approach with Safe-visor Architecture
论文作者
论文摘要
在本文中，我们提出了一种用于沙箱未验证控制器的安全visor体系结构的构建方案，例如基于人工智能的（又称基于AI的基于AI）的控制器，在两个玩家的非合作随机游戏中。具体而言，我们利用基于抽象的方法来构建主管，该主管检查并决定是否接受未验证的控制器提供的输入，以及提供后备控制输入的安全顾问，以确保没有验证的控制器被拒绝。此外，通过利用（$ε，δ$） - 原始游戏与其有限抽象之间的近似概率关系，我们就确定性有限自动机（DFA）建模的安全规范提供了正式的安全保证，而未经验证控制器的功能仍然被利用。为了显示提出的结果的有效性，我们将其应用于四个四个跟踪移动地面车辆的控制问题，在该问题中，使用基于AI的未验证控制器来控制四极管。
In this paper, we propose a construction scheme for a Safe-visor architecture for sandboxing unverified controllers, e.g., artificial intelligence-based (a.k.a. AI-based) controllers, in two-players non-cooperative stochastic games. Concretely, we leverage abstraction-based approaches to construct a supervisor that checks and decides whether or not to accept the inputs provided by the unverified controller, and a safety advisor that provides fallback control inputs to ensure safety whenever the unverified controller is rejected. Moreover, by leveraging an ($ε,δ$)-approximate probabilistic relation between the original game and its finite abstraction, we provide a formal safety guarantee with respect to safety specifications modeled by deterministic finite automata (DFA), while the functionality of the unverified controllers is still exploited. To show the effectiveness of the proposed results, we apply them to a control problem of a quadrotor tracking a moving ground vehicle, in which an AI-based unverified controller is employed to control the quadrotor.
