This paper presents an augmented situation calculus-based approach to model autonomous computing paradigm in ubiquitous information services. To make it practical for commercial development and easier to support autonomous paradigm imposed by ubiquitous information services, we made improvements based on Reiter's standard situation calculus. First we explore the inherent relationship between fluents and evolution: since not all fluents contribute to systems' evolution and some fluents can be derived from some others, we define those fluents that are sufficient and necessary to determine evolutional potential as decisive fluents, and then we prove that their successor states wrt to deterministic complex actions satisfy Markov property. Then, within the calculus framework we build, we introduce validity theory to model the autonomous services with application-specific validity requirements, including: validity fluents to axiomatize validity requirements, heuristic multiple alternative service choices ranging from complete acceptance, partial acceptance, to complete rejection, and validity-ensured policy to comprise such alternative service choices into organic, autonomously-computable services. Our approach is demonstrated by a ubiquitous calendaring service, ACS, throughout the paper.
State Key Laboratory for Novel Software Technology \& School of Artificial Intelligence, Nanjing University, China School of Informatics, The University of Edinburgh, UK
Using T-Norm Based Uncertainty Calculi in a Naval Situation Assessment Application
General Electric Corporate Research and Development（通用电气公司企业研究与开发中心）
RUM（Reasoning with Uncertainty Module）是一个基于KEE的集成软件工具，KEE是一个用面向对象语言实现的框架系统。RUM的体系结构由三层组成：表示层、推理层和控制层。表示层基于帧状数据结构，其捕获在推理层中使用的不确定性信息和在控制层中使用的不确定性元信息。推理层提供了五个基于T范数的不确定性演算的选择，用于执行信息的交集、分离、并集和池化。控制层使用元信息为每个上下文选择适当的演算，并解决信息中的最终无知或冲突。这一层还提供了一个上下文机制，使系统能够专注于知识库的相关部分，以及一个不确定性信念修正系统，该系统增量地更新非循环有向演绎图中的良构公式（wffs）的确定性值。RUM已经在海军和空中态势评估（SA）的一系列实验中进行了测试和验证，包括相关报告和跟踪，定位和分类平台，以及识别意图和威胁。最后给出了一个海上态势评估的实例。开发这些实验的测试平台环境由LOTTA提供，LOTTA是Flavors中实现的符号模拟器。该模拟器在多玩家对抗游戏中保持时变情况，玩家必须根据不确定和不完整的数据做出决策。RUM已被用于协助LOTTA玩家之一执行SA任务。
