Self-Evolving Adaptive Interfaces
bullet

A Research Project under the DAGSI/AFRL Aerospace Research Program

Project Description

  • Abstract

    • In dynamic situations where task requirements and operator states can change from moment to moment, such as those found in battle conflicts or agile work environments, a fixed interface only provides the best mappings between the user and technology over the narrow predefined range fixed during design, producing suboptimal performance outside of this design envelope. Given the very dynamic and ever-changing situations addressed by both military and global industry, a real-time rapidly customizable interface between the human and technology is required to continuously maintain the best match between these entities for maximizing both the personnel and technology investments.

    The research aim of this project is to develop and test operator-system interfaces which adapt to the operator's state in real-time and thus provide the operator with the right information at the right time. Providing this capability will enable operators to make faster and more accurate decisions. The performance enhancement provided by adaptive interafaces will reduce the number of required operators, as well as reduce training requirements by enhancing the novice operator's performance ability.

    Previous research in adaptive interfaces has focused primarily on identifying and measuring operator state variables that could prompt adaptation of interface features and dynamic function allocation in noncomplex task environments. To date, the testing of various adaptive interface concepts have been empirically- based, with a focus on testing combinations of variables rather than developing or validating a model. This project addresses a need in the scientific body of knowledge by moving on from the previous empirical studies. It brings together a team of experts in a variety of disciplines and multiple universitites to develop a biologically-inspired, model-based adaptive interface architecture with a different and potentially more robust foundation for interface adaptation.


     
  • Goals and Objectives

    • The project goal is to investigate a new paradigm for an adaptive interface architecture which has the capacity to be self-evolving. This effort extrapolates to the biological sciences and other approaches for novel evolutionary models upon which to build innovative mechanisms of adaptation. Physiological, morphological, and behavioural responses can be short-term adjustuments on the scale of ecological time or adaptation on the scale of evolutionary time.

    The project's focus is to develop an adaptive model that meets a set of criteria. The model must:
  • incorporate representations of operator states.
  • represent interface features which are adaptable.
  • represent cognitive processing in a computational framework.
  • provide measures of merit for matches between the input state variables and interface adaptation permutations.
  • operate in a real-time mode.
  • incorporate self-evolving mechanisms.

    •  
  • Activities

    • The research has five tasks to deliver -- three in phase one of the project and the remainder in phase two. In addition, a team-taught course will be offered.

    Tasks:
    1. Critically review potential foundations for the self-evolving adaptive model.
    2. Create a Web site warehousing the international work on adaptive interfaces
    3. Develop the theoretical paradigm for the self-evolving adaptive mechanism.
    4. Develop and test the new mechanism in a computational environment.
    5. Validate the mechanism in the Air Force Research Laboratory's Synthesized Immersion Research Environment (SIRE).

    Major Participants

    References and Related Links


     
     
     
     

    This page was last updated September 25, 2000.  Please send comments to Web master