In real-time control systems, the value of a control decision depends not only on the correctness of the decision but also on the time when that decision is available. Recent work in real-time decision making has used machine learning techniques to automatically construct reactive controllers, that is, controllers with little or no internal state and low time complexity pathways between sensors and effectors. This paper presents research on 1) how a problem representation affects the trade-offs between space and performance, and 2) off -line versus on-line approaches for collecting training examples when using machine learning techniques to construct reactive controllers. Empirical results show that for a partially observable problem both the inclusion of history information in the problem representation and the use of on-line rather than off -line learning can improve the performance of the reactive controller. / Graduation date: 1994

A microcomputer-based process controller has been developed to produce porous membrane material. The production process is based on stretching the material in a constant temperature solvent bath. This thesis describes the hardware and software designed to direct and monitor the process. A VIC 20 is used as the process-controlling microcomputer. The system features two dedicated motor controllers and two channels for controlling temperature. The motor controllers determine the material feed rate and rate of stretch. The temperature controllers keep the system at a selectable constant temperature. An interactive assembly language program directs the entire process and monitors the controlled variables. A complete description of the interface and temperature control circuitry is given. The software used to direct the process is also discussed and presented. / Master of Science