The SHADOW Digital Twin (Supervisory Human Analog for Decision-making and Operational Work-state)

With Mars one-way comms delays up to 22 minutes, flight crew are the safety-critical layer, supervising highly automated systems without real-time ground support. Yet routine monitoring demands little attention, and planners cannot verify if a crew member is engaged. Current digital twins replicate vehicles and habitats, not the crew supervising them. A credible digital twin requires bidirectional coupling, real-time state synchronization, and predictive projection to the host system. Hardware state is directly measurable, whereas cognitive readiness must be inferred from non-invasive signals alone. SHADOW must start generalizable and tune to a specific crew member, a dual constraint that strains models built for one or the other. Meeting that bar gives each astronaut a uniquely calibrated twin. This project aims to operationalize human performance science by fusing bottom-up non-invasive sensors (eye tracking, overt behavior) with top-down theory. Bidirectionally coupled to the host system, it infers readiness, synchronizes state in real time, and feeds projections back.

For future Mars missions with Mars comms delays up to 22 min crew will supervise automation with no real-time ground support. The approach in this project to enable technology/methods that frames human as resilient layer, not a failure source in such scenarios. Target outcomes include: Generalizable base model from non-invasive inputs (eye tracking, overt behavior), Finite state machine then hidden Markov model developed to classify engaged vs. displaced attention

This is a mature technology (TRL 7+) — the realistic path in is usually NASA's Technology Transfer Program: licensing an existing NASA patent, or a Space Act Agreement to use NASA facilities/expertise directly. NASA also runs a startup licensing program with no upfront fee for companies formed to commercialize a specific NASA technology.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.