Raytheon BBN Technologies

In the information age, organizations have access to vast amounts of data. The challenge lies in sifting through and understanding the particular data that pertains to the task at hand. The cognitive approach to Human-Machine Collaboration is the solution to information overload.

Benefit of investing in the Cognitive Human-Machine Collaboration.

Reducing the cognitive burden on users = more accurate, faster decision making = time saved and fewer mistakes = total organization savings.

Who benefits?

Organizations faced with large amounts of both static and dynamic data that must be quickly analyzed, understood, and acted upon benefit from Human-Machine Collaboration. In environments where priorities and available information are constantly in flux, Human-Machine Collaboration provides a path to optimal decision making.

Appropriate applications include:

• Military transportation logistics planning
• Medical Research
• Financial Institutions
• Air Traffic Control Centers

Raytheon BBN Technologies designs tools through a Work Centered Design Methodology.

The central idea in this methodology is to design tools that support the users in the work they perform. Although this sounds obvious, most tools are currently designed around data first rather than work goals. Knowledge acquisition is the first step in understanding the information needs of a potential user and, more importantly, how this information is used in decision making. Data, or information is appropriately distilled and presented to users through cognitive visualizations. These visualizations filter out what is not needed in a given decision space and alert users to the most pertinent information. Depending on the task at hand in the work flow, different visualizations, alerts, and optimization options are presented and/or available to the user. Applied mathematics, such as constraint based scheduling or simulation & modeling techniques, comprise the underlying technologies in any given customer solution.

Work Centered Design Methodology

What are the design implications of effective collaborative automation?

• Importance of enabling users to be active partners:
• Observability: A shared representation enables both the user and the automation to understand and contribute to the problem specification.
• Directability: Multiple mechanisms are provided to modify default assumptions and guide problem solution.
• Importance of fostering better solutions than would be possible by either element of the Joint-Cognitive System working alone:
• Broadening: Broadening the set of candidate solutions explored and the range of factors considered in evaluating these solutions.
• Adaptability: Enhancing the ability to adapt to characteristics of the situation.

This model supports users in integrating the results of the automated process into their own workspace and workflow.