Caroline C. Hayes

Automating process planning: Using feature interactions to guide search

Abstract Machinist is an expert system that automatically makes process plans for fabricating metal parts on a CNC machine tool. It is part of an overall effort to automate the job shop. The type of parts it handles are prismatic, with features cut into one or more sides. Parts of this type are difficult because features on different sides may interact with each other: cutting one group of features first may make the part such an odd shape that it is difficult to clamp for subsequent operations. These interactions must be carefully considered when grouping and ordering the machining operations. The machinist program has been designed to be an integral part of CAD systems, facilitating the generation of manufacturing plans.

Fox-ga: A genetic algorithm for generating and analyzing battlefield courses of action

This paper describes FOX-GA, a genetic algorithm (GA) that generates and evaluates plans in the complex domain of military maneuver planning. FOX-GAs contributions are to demonstrate an effective application of GA technology to a complex real world planning problem, and to provide an understanding of the properties needed in a GA solution to meet the challenges of decision support in complex domains. Previous obstacles to applying GA technology to maneuver planning include the lack of efficient algorithms for determining the fitn ess of plans. Detailed simulations would ideally be used to evaluate these plans, but most such simulations typically require several hours to assess a single plan. Since a GA needs to quickly generate and evaluate thousands of plans, these methods are too slow. To solve this problem we developed an efficient evaluator (wargamer) that uses course-grained representations of this problem domain to allow appropriate yet intelligent trade-offs between computational efficiency and accuracy. An additional challenge was that users needed a diverse set of significantly different plan options from which to choose. Typical GAs tend to develop a group of best solutions that may be very similar (or identical) to each other. This may not provide users with sufficient choice. We addressed this problem by adding a niching strategy to the selection mechanism to insure diversity in the solution set, providing users with a more satisfactory range of choices. FOX-GAs impact will be in providing decision support to time constrained and cognitively overloaded battlestaff to help them rapidly explore options, create plans, and better cope with the information demands of modern warfare.

Toward a Characterization of Adaptive Systems: A Framework for Researchers and System Designers

Objective: This article presents a systematic framework characterizing adaptive systems. Background: Adaptive systems are those that can appropriately modify their behavior to fit the current context. This concept is appealing because it offers the possibility of creating computer assistants that behave like good human assistants who can provide what is needed without being asked. However, the majority of adaptive systems have been experimental rather than practical because of the technical challenges in accurately perceiving and interpreting users’ current cognitive state; integrating cognitive state, environment, and task information; and using it to predict users’ current needs. The authors anticipate that recent developments in neurological and physiological sensors to identify users’ cognitive state will increase interest in adaptive systems research and practice over the next few years. Method: To inform future efforts in adaptive sys-tems, this work provides an organizing framework for characterizing adaptive systems, identifying consider-ations and implications, and suggesting future research issues. Results: A two-part framework is presented that (a) categorizes ways in which adaptive systems can modify their behavior and (b) characterizes trigger mechanisms through which adaptive systems can sense the current situation and decide how to adapt. Conclusion: The framework provided in this article provides a tool for organizing and informing past, present, and future research and development efforts in adaptive systems.

An intelligent-agent framework for concurrent product design and planning

This paper proposes a multi-agent framework to develop product design and planning using the concurrent engineering approach. The ideas in the framework draw on design-team behavior in many domains. The goal is to provide information that will help teams of designers, engineers and managers from various functional areas improve initial designs so that they satisfy a wider variety of concerns. Our model provides support to bring together constraints from the different team members in the development cycle. By integrating downstream constraints into the design phase, we reduce the need for redesign (due to design mistakes) later in the product development cycle. Our framework integrates a blackboard architecture with an intelligent agent (IA) network. Our methodology uses conflict-resolution (CR) techniques and design-improvement suggestions to refine the initial product design, and process plan generation and simulation to verify the manufacturability of the design. The contributions of the paper are threefold. First, our framework provides a more realistic way of modeling design teams by providing a way to model an individual team members perspective as a segment of a continuum of task knowledge. Second, we identify the essential components of concurrent engineering needs, and develop a framework for integrating these components so as to ensure adequate coordination among the processes involved. Third, our methodology uniquely meshes together design constraints with factory resource considerations, so that the final product design is ensured to be feasible and manufacturable.

New Directions in Design for Manufacturing

This paper gives an overview of research that is expanding the domain of design for manufacturing (DFM) into new and important areas. This paper covers DFM and concurrent engineering, DFM for conceptual design, DFM for embodiment design, DFM for detailed design, design for production, platform design for reducing time-to-market, design for system quality, design for life cycle costs, and design for environment. The paper concludes with some general guidelines that suggest how manufacturing firms can develop useful, effective DFM tools.

Custom-Cut: a customizable feature recognizer

Abstract The tools and processes available in a given shop greatly influence the way in which manufacturers view a part and the way in which they decompose it into machinable volumes, or features. Likewise, a feature recognizer should be able to produce a different feature decomposition when different tools are available. Additionally, it should be easy for a user to add new tool descriptions to the system in order to maintain and customize the feature recognizer. We address this challenge in two parts. First, we present an extensible representation which allows users to easily add their own custom tool descriptions to a feature recognizer’s knowledge base. Second, we present C ustom -C ut , a tool-based, resource-adaptive feature recognizer. C ustom -C ut accepts the user-defined cutting tools as input and automatically identifies the areas of the part that can be cut using the custom tools. We call C ustom -C ut resource-adaptive because the features it identifies will be different if it is given different cutting tools. The advantages of this is that it is easier for the user to maintain and customize and provides greater assurance that the features identifies are actually machinable with the given set of equipment.

The CAD/CAM Interface: A 25-Year Retrospective

The vision of fully automated manufacturing processes was conceived when computers were first used to control industrial equipment. But realizing this goal has not been easy; the difficulties of generating manufacturing information directly from computer aided design (CAD) data continued to challenge researchers for over 25 years. Although the extraction of coordinate geometry has always been straightforward, identifying the semantic structures (i.e., features) needed for reasoning about a components function and manufacturability has proved much more difficult. Consequently the programming of computer controlled manufacturing processes such as milling, cutting, turning and even the various lamination systems (e.g., SLA, SLS) has remained largely computer aided rather than entirely automated. This paper summarizes generic difficulties inherent in the development of feature based CAD/CAM (computer aided manufacturing) interfaces and presents two alternative perspectives on developments in manufacturing integration research that have occurred over the last 25 years. The first perspective presents developments in terms of technology drivers including progress in computational algorithms, enhanced design environments and faster computers. The second perspective describes challenges that arise in specific manufacturing applications including multiaxis machining, laminates, and sheet metal parts. The paper concludes by identifying possible directions for future research in this area.

Considering Etiquette in the Design of an Adaptive System

In this article, the authors empirically assess the costs and benefits of designing an adaptive system to follow social conventions regarding the appropriateness of interruptions. Interruption management is one area within the larger topic of automation etiquette. The authors tested these concepts in an outdoor environment using the Communications Scheduler, a wearable adaptive system that classifies users’ cognitive state via brain and heart sensors and adapts its interactions. Designed to help dismounted soldiers, it manages communications in much the same way as a good administrative assistant. Depending on a combination of message priority, user workload, and system state, it decides whether to interrupt the user’s current tasks. The system supports decision makers in two innovative ways: It reliably measures a mobile user’s cognitive workload to adapt its behavior, and it implements rules of etiquette adapted from human-human interactions to improve human-computer interactions. Results indicate costs and benefits to both interrupting and refraining from interrupting. When users were overloaded, primary task performance was improved by managing interruptions. However, overall situation awareness on secondary tasks suffered. This work empirically quantifies costs and benefits of “appropriate” interruption behaviors, demonstrating the value of designing adaptive agents that follow social conventions for interactions with humans.

CoRAVEN: modeling and design of a multimedia intelligent infrastructure for collaborative intelligence analysis

Intelligence analysis is one of the major functions performed by an Army staff in battlefield management. In particular, intelligence analysts develop intelligence requirements based on the commanders information requirements, develop a collection plan, and then monitor messages from the battlefield with respect to the commanders information requirements. The goal of the CoRAVEN project is to develop an intelligent collaborative multimedia system to support intelligence analysts. Key ingredients of our design approach include: (1) significant knowledge engineering activities with domain experts, (2) representation of an explicit model of reasoning and activity to drive design, (3) the use of Bayesian belief networks as a way to structure inferences that relate observable data to the commanders information requirements, (4) collaborative graphical user interfaces to provide flexible support for the multiple tasks in which analysts are engaged, (5) sonification of data streams and alarms to support enhanced situation awareness, (6) detailed psychological studies of reasoning and judgment under uncertainty, and (7) iterative prototyping of candidate designs with domain experts for both formative and summative evaluation. The paper discusses our current progress on all these fronts.

Uncertainty Visualizations Helping Decision Makers Become More Aware of Uncertainty and Its Implications

Uncertainty is inherent in all real work contexts; it creates ambiguities that make decision making difficult. To help decision makers manage ambiguity, the authors developed and evaluated a domain-independent decision support system (DSS), the Uncertainty DSS. It is designed to help decision makers recognize situations in which uncertainty creates ambiguity in their choices and to identify information that can help reduce that ambiguity. It does so by providing an uncertainty visualization, which shows when the range of possible values for two or more alternatives overlap, indicating that one cannot identify the best alternative given the current information. To evaluate the Uncertainty DSS, the authors created a pared-down version, the Certainty DSS, which provides no uncertainty visualizations. They recruited 22 engineering designers and asked them compare alternative designs from real, ongoing design projects using no DSS, the Certainty DSS, and the Uncertainty DSS. The authors found that without the visualizations, participants did not distinguish between ambiguous and unambiguous choices. However, the Uncertainty DSS improved participants’ ability to recognize ambiguous decision situations. Additionally, it increased the likelihood that participants would form plans to seek clarifying information. These results suggest that a relatively simple visualization can change the way in which designers think about decision choices.