Cognitive Systems Engineering (CSE) Methods to Support Adaptive, Integrated Anomaly Response

The proposed project aims to tailor cognitive systems engineering methods to support the design of Fault Detection, Isolation, and Recovery (FDIR) capabilities intended for remote smart habitats and NASA’s Moon to Mars initiative. We will adapt the Integrated Cognitive Analysis for Human-Machine Teaming (ICA-HMT) strategy, developed and exercised previously as part of the Army’s Future Vertical Lift program to understand the envisioned world for future rotorcraft that leverages advanced automation and operates in dynamic, time-critical and high-risk contexts. For this project, we will conduct an in-depth Cognitive Task Analysis (CTA) to understand and document the envisioned world of remote smart habitats and identify cognitive requirements associated with deep space operational challenges such as intermittently occupied smart habitats, limited communications bandwidth, and significant communication latencies. CTA findings will be used to generate design recommendations for integrated human-autonomy system configurations that can then be evaluated using Work Models that Compute (WMC), a modeling and simulation framework. WMC is designed to model elements of collective work such as workload, interdependencies, and tradeoffs, incorporating macrocognitive aspects of the work that are not easily observed (e.g., sensemaking, decision making). We further propose the design of visualizations that enable developers to “what-if” and explore tradeoffs between different teaming configurations. Phase I objectives include identifying high-consequence FDIR use cases, extending WMC to include the cognitive aspects of the work that enable modeling of various integrated human-autonomy teaming configurations, and assessing feasibility of the proposed approach. This team includes Applied Decision Science, experts in cognitive task analysis; Dr. Martijn Ijtmsa of the Ohio State University, expert in WMC; and former astronaut James ‘Mash’ Dutton.