The Design of Real-Time Expert Systems for Autonomous Vehicles

1988年12月，海洋系统工程实验室(MSEL)开始了一项由国家科学基金资助的计划(批准号：EID-8818406)，研究用于自主水下航行器系统的基于知识的系统设计中的关键问题。其目的是了解与在实时领域中利用这些基于知识的系统有关的一些问题。这些努力的重点是建立一个建立在实时操作系统之上的符号处理环境。这项工作建立在初步工作结果的基础上，反映了在该计划的初始阶段开发的见解。调查将在两年的时间内完成，并将导致为自动潜航器(AUV)系统中运行的专家系统实施智能实时调度器。它定义了根据我们先前在设计实时专家系统中所做的工作而指定的标准来开发调度算法的努力。这项工作的成果将是一种独立于领域的调度算法，适用于多个知识源以时间受限的方式交互的任何环境。

In December 1988, the Marine Systems Engineering Laboratory (MSEL) began a program, funded by the National Science Foundation (Grant No. EID-8818406), to investigate the key issues in the design of knowledge-based systems for use in Autonomous Underwater Vehicle (AUV) systems. It was directed at understanding some of the problems associated with utilizing these knowledge-based systems in real time domains. The efforts focused on establishing a symbolic processing environment which would exist on top of a real time operating system. This effort which builds on the results of the initial work, reflects the insights which were developed during the initial phase of this program. The investigations will be accomplished over a two year period and will result in the implementation of a intelligent real-time scheduler for expert systems running in Autonomous Undersea Vehicle (AUV) systems. It defines an effort to develop a scheduling algorithm in accordance with the criteria specified as a result of our previous work in designing real-time expert systems. The product of this effort will be a domain-independent scheduling algorithm suitable for use in any environment where multiple knowledge sources interact in a time-constrained fashion.