Workflow agents versus expert systems: Problem solving methods in work systems design

Abstract

During the 1980s, a community of artificial intelligence researchers became interested in formalizing problem solving methods (PSMs) as part of an effort called “second-generation expert systems.” We provide an example of how we are applying second-generation expert systems concepts in an agent-based system for space flight operations, the orbital communications adapter mirroring system (OCAMS), which was developed in the Brahms multiagent framework. Brahms modeling language provides an ontology for simulating work practices, including groups, agents, activities, communications, movements, and geographic areas.Activitiesare a behavioral unit of analysis to be contrasted withtasks, a functional unit of analysis. Problem solving occurs in the context of activities in the service of tasks; appropriate PSMs depend on the context: which people/roles are participating, what tools are available, how the results will be evaluated, and so forth. A work practice simulation facilitates designing workflow tools that appropriately interact with the physical and organizational context in which work occurs. OCAMS was developed using a simulation-to-implementation methodology, in which a prototype workflow tool was embedded in a Brahms simulation of how people would use the tool. The reusable components in a workflow system like OCAMS include entire “problem solvers” (e.g., a planning subsystem), interoperability frameworks, and agents that inspect and change the world. Thus, a tool kit for building workflow tools requires more than a library of PSMs, which play a relatively small role in the overall multiagent, systems-integration architecture. Our research concern has shifted to situations that may arise that are outside the OCAMS' capability. In practical decision making, people must reflect on the validity of their models. As programs becoming actors in the workplace, we need to develop systems that help people to understand the limitations of the models that drive the automated operations, which means in part detecting when the formalizations in the system are inadequate.

Situated cognition

“…that cognition is for action and that embodiment and the situated nature of adaptive action are crucial constraints’ (Ref , p. 104). The influence of the situated cognition perspective on cognitive science can be seen, among others, in the shift from intelligent tutoring systems research to systems that emphasize interactivity …”

“…The influence of the situated cognition perspective on cognitive science can be seen, among others, in the shift from intelligent tutoring systems research to systems that emphasize interactivity. 5 In the following, we begin by circumscribing situated cognition as a set of interlocked theses and proceed to describe the historical context in which these theses emerged. We then articulate the evidence mobilized in support of these theses from (1) empirical studies and (2) modeling studies.…”

Software-engineering challenges of building and deploying reusable problem solvers

“…He argues that there is a poor match between the techniques provided by PSMs and the way in which human cognition operates. Clancey et al (2009, this issue) assert that the PSM approach fails to consider the workflow processes in system design. He claims that the approach assumes that PSMs are embedded in relatively static systems and that, as a result, the systems that they automate are not sufficiently flexible to address the situated behavior of many computational systems.…”

Agent-Based Modeling and Simulation of Collaborative Air Traffic Flow Management using Brahms

“…Brahms [4,5] is an ABMS, developed for over a decade, as a way to model and simulate people within a social and physical world. It has found multiple applications at NASA and is currently operational within mission control handling the previous human task of synchronizing files between the International Space Station and mission control [12,13].…”