TECHNOLOGY AREAS: Human Systems

ACQUISITION PROGRAM: Total Ship Training System - PEO IWS 7C

OBJECTIVE: Develop an innovative adaptive training tool suite with the goal of imparting adaptive expertise to the learner -- including intuition, critical/creative thinking, decision making, problem solving, and team interaction skills -- while compressing the learning experience by optimally tailoring experiences, in real-time, to current cognitive and physiological states of the learner.

DESCRIPTION: The at-sea environment is one of the least forgiving of errors, particularly in decision making and situation awareness. Commanders and their crews must be able to adjust to unforeseen threats and make accurate and timely decisions in the face of vast streams of complex and sometimes conflicting data with varying levels of detail and reliability, while working in a distracting and crowded environment. Surface and subsurface crews in the future will be required to report onboard with a greater level of skills, rather than relying extensively on "on-the-job" training to come up to speed. Reduced manning also drives Sailors to understand and execute more than one traditional job. These challenges require a new direction in on-board and off-board training approaches.

Adaptive simulation-based training has the potential to present individual trainees and teams with the optimal mix of experiences and instruction to rapidly develop robust and effective decision making skills and other complex cognitive processes to deal with uncertain threats. However, the development of this type of training capability requires an emphasis on furthering methods and technologies for training the skill of adaptive expertise (Burke, Pierce, & Salas, 2006; Dorsey, Mueller-Hanson, & Pulakos, 2006; Holyoak, 1991; Tillson et al., 2005). Further, it requires additional technical capabilities for continuous performance measurement and assessment, and empirically validated instructional interventions. Ideally, a full spectrum measurement and diagnostic approach should be developed. A comprehensive picture of a trainee�s state of knowledge, skills and abilities can only be developed through an integration of multiple sources of data. Integrating and evaluating these data also requires powerful and sophisticated models of expert performance. In order to support adaptive training systems, it is necessary to build, execute, and manipulate these models in real-time. Finally, while advanced display capabilities and intelligent agent technology, combined with the advanced performance assessment capabilities addressed above, have opened a host of possibilities for adapting training (such as real-time feedback, real-time scenario modification and automated cueing and scaffolding strategies), what is still needed is empirically based guidance to drive the optimal selection of adaptive instructional mitigation given the current context (learner�s state, training domain).

PHASE I: Develop an adaptive training framework. The components in the framework should build on and extend the state-of-the-art capabilities in performance measurement (including neurophysiological indices), modeling and assessment techniques, and learning sciences. The components in the framework should work within an open systems architecture.

PHASE II: Develop a prototype suite of adaptive training tools based on the framework established in Phase I. Validate the tools through empirical evaluations with the targeted user community.

PHASE III: Produce and market the suite of adaptive training tools for integration with ship and submarine training acquisition programs including the Total Ship Training System and submarine Bridge Team Trainer.

PRIVATE SECTOR COMMERCIAL POTENTIAL/DUAL-USE APPLICATIONS: The suite of tools will have widespread applications to military, government, and private sector organizations in which fewer personnel are required to operate the same tasks and missions without degraded performance, i.e., the training is required to be adaptive to the learner to compress learning time and increase competency levels.

REFERENCES:
1. Burke, S., Pierce, L., & Salas, E. (2006). Understanding Adaptability: A Prerequisite for Effective Performance Within Complex Environments. Cambridge, MA: Elsevier Science.

2. Dorsey, D., Mueller-Hanson, R., & Pulakos, E. (2006, July). Adaptability and adaptive performance: Current findings and future directions for building adaptive forces. 2006 Army Science of Learning Workshop, Hampton, VA. (Available on-line http://isupport.geo-centers.com/slw/WhitePapers/PDRIWhitepaperArmySOL15July.doc)

3. Holyoak, K. J. (1991). Symbolic connectionism: toward third-generation theories of expertise. In K.A. Ericsson & J. Smith (Eds.), Towards a General Theory of Expertise: Prospects and Limits. Cambridge: Cambridge University Press.

4. Tillson, J., Freeman, W., Burns, W., Michel, J., LeCuyer, J., Scales, R., et al. (2005). Learning to adapt to asymmetric threats. (IDA) Document D-3114). Alexandria, VA: Institute for Defense Analyses (DTIC No. ADA442427)

KEYWORDS: adaptive training; measurement; assessment; modeling; learning sciences; adaptive expertise