Edge Readiness Monitoring for Space Operations Using Samsung Wearables (Offline-First Safety Analytics)
Engineering, IT, Mathematics and Statistics
PLEASE NOTE
- Due to the sensitivity and security of this project, students must have Australian Citizenship or Permanent Residency to apply.
- This research internship is funded in partnership with Space Research Network (SRN), students must be from an SRN member university to apply. This includes most NSW Universities and ANU (USyd, UTS, UNSW, MQ, UoN, WSU, UoW, ANU).
ABOUT THE INDUSTRY PARTNER
Fortifyedge.ai is an Australian AI company building human-centered edge intelligence for frontline workers. Leveraging Samsung wearables, on-device TinyML, and privacy-preserving sensor fusion, Fortifyedge.ai delivers real-time biometric authentication, cognitive load monitoring, and situational awareness without reliance on the cloud. The platform is deployed across defense, public safety, and critical infrastructure sectors for secure, offline AI decision support.
WHAT’S IN IT FOR YOU?
- Work on NSW Space Research Network–aligned applied research translating heavy-vehicle fatigue detection into readiness monitoring for space operations and space supply-chain shift work.
- Hands-on experience building an offline-first prototype on Samsung hardware (Galaxy Watch 8 and Knox-managed tablets; optional Samsung XR for training/visualisation).
- Apply practical methods for multi-sensor signal processing, model evaluation, and human-in-the-loop safety design in high-consequence environments.
- Apply state-of-the-art physical AI – world-model concepts to multimodal human-performance data.
- Deliver a demonstrable prototype and an evaluation report suitable for operational stakeholders, with pathways to publication/continued PhD work
RESEARCH TO BE CONDUCTED
- Define translational requirements across (A) regional heavy-vehicle driving and (B) space operations (astronaut training/operations and space supply-chain logistics). Identify shared constraints: intermittent communications, fatigue accumulation, circadian disruption, noise/vibration, heat stress, and high consequence of error. Agree on readiness indicators, labels/proxies, and a privacy-first data handling plan.
- Build a multi-sensor data pipeline using Samsung Galaxy Watch 8 signals plus task/shift context. Develop an individualized readiness scoring approach that learns baseline patterns and detects meaningful deviations associated with fatigue/cognitive overload. Implement offline on-device inference and haptic alerts, with configurable thresholds and safe escalation rules.
- Create supervisor-friendly outputs for mission/shift planning (trend summaries, circadian risk windows, heatmaps) and an explainable event log designed for safety governance (what happened, when, and recommended mitigation actions).
- Evaluate performance and alert burden, refine thresholds, and produce a translation report mapping findings to a space pilot concept (e.g., astronaut training analogs, spaceport logistics shift work) and a Phase 2 controlled-trial plan.
SKILLS WISH LIST
If you’re a postgraduate research student and meet some or all the below we want to hear from you. We strongly encourage women, indigenous and disadvantaged candidates to apply:
- Strong Python skills and applied ML/data science (time-series modelling, anomaly detection, basic signal processing).
- Experience working with wearable or sensor data (heart rate/HRV, temperature, activity, sleep) and building data pipelines.
- Mobile/edge engineering interest (Android/on-device inference concepts, offline-first design, performance constraints).
- Evaluation skills: precision/recall, calibration, threshold tuning, and alert-fatigue management.
- Human factors mindset: designing interventions that are usable in real operations (haptics, minimal distraction, safety-first UX).
- Interest in space operations translation (astronaut readiness, circadian disruption, spaceport/launch logistics safety).
- Bonus: familiarity with enterprise mobility/security concepts (Knox) and dashboard/reporting. LLM/VLM prompting for structured summaries; MLOps; privacy/security-by-design (Knox/enterprise mobility)
- Rapid MVP development utilising Claude, google AI Studio etc.
RESEARCH OUTCOMES
- A validated “Operator Readiness World Model” embedding + risk scoring pipeline transferable from heavy-vehicle operations to space contexts (astronaut training/operations and space supply-chain shift work).
- Offline-first edge prototype on Samsung devices (Watch 8 haptics + tablet app) with configurable thresholds, escalation logic, and auditable logging suited to comms-limited environments.
- Evaluation pack: detection performance, calibration, alert-fatigue analysis, and recommended readiness thresholds by task class (driving analogs → IVA/EVA/logistics analogs).
- Supervisor outputs: circadian risk windows, trend heatmaps, and recovery recommendations to inform mission planning, shift design, and safety governance.
- Packaged handover: code, model cards, privacy notes, and a Phase 2 pilot plan for space analog trials (habitat/spaceport logistics, astronaut training simulations, XR-based task rehearsals).
ADDITIONAL DETAILS
The intern will receive $3,300 per month of the internship, usually in the form of scholarship payments.
It is expected that the intern will primarily undertake this research project during regular business hours and maintain contact with their academic mentor throughout the internship either through face-to-face or phone meetings as appropriate.
The intern and their academic mentor will have the opportunity to negotiate the project’s scope, milestones and timeline during the project planning stage.
Please note, applications are reviewed regularly and this internship may be filled prior to the advertised closing date if a suitable applicant is identified. Early submissions are encouraged.
INTERNSHIP CONTACT
CONNECT WITH APR.INTERN
