2022 I/ITSEC: STEEL-R Paper (Extending the TLA for Experiential Learning; Best Paper PSMA Subcommittee)

User documentation

Defense-wide efforts are underway to modernize learning technologies and increase capabilities related to warfighter performance. Many investments focus on discrete training experiences, which does not provide a platform for longitudinally assessing the competencies and progression of learners or the efficacy of training systems. Longitudinal assessments are needed both for training purposes and to support the transfer of training systems into the acquisition process.

The STE (Synthetic Training Environment) Experiential Learning for Readiness (STEEL-R) project addresses the challenge of gathering and analyzing longitudinal training and performance data by establishing a common data interoperability layer that collects evidence through a competency-based experiential learning model. The STEEL-R architecture is based on and extends the US Advanced Distributed Learning (ADL) initiative’s Total Learning Architecture (TLA) to function across an ecosystem of synthetic and live training environments. This approach provides data traceability, supports evidence-based training decisions, and results in datasets that can inform acquisition teams and reduce the need to manually collect data when transitioning from research to acquisition.

This paper starts by presenting the STEEL-R architecture, in which xAPI, the Generalized Intelligent Framework for Tutoring (GIFT), Learning Record Stores (LRSs), and the Competency and Skills System (CaSS) - all open source and developed for the DoD - play central roles. GIFT is used to orchestrate data from training exercises ranging from game-like VBS exercises to live field exercises in which soldiers are equipped with wearable sensors. The paper then discusses the data models used and data is collected over time and transformed into standardized patterns that can be used to produce fully traceable evidence-based decisions concerning trainees. The last section of the paper discusses the implications of this approach for evaluating system performance and how this work will aid DoD acquisition teams.


2022_iitsec_22461_steelr_Enhancing_TLA.pdf (804 KB) Goldberg, Ben, 12/20/2022 09:35 AM [D/L : 1185]