NaviGateAI: An Interoperable Digital Twin Decision Support Platform for Emergency Response and Situational Awareness
| Reference number | |
| Coordinator | Chalmers Tekniska Högskola AB - Chalmers tekniska högskola Department of Computer Science and Engineering |
| Funding from Vinnova | SEK 9 065 400 |
| Project duration | April 2026 - April 2028 |
| Status | Ongoing |
| Venture | Advanced digitalization - Industrial needs-driven innovation |
| Call | Industrial applied AI by advanced digitalization 2026 |
Purpose and goal
NaviGateAI develops and field-validates an interoperable real-time decision support platform that strengthens situational awareness in emergency response. The project delivers a TRL 7 MVP that fuses drone video, wearable and helmet sensors, thermal and visual streams, IMU, and a priori building and geospatial data into a continuously updated 3D operational picture with prioritized, explainable recommendations for incident command, supporting fast "how", "why", and "what-if" queries.
Expected effects and result
Results: a validated TRL 7 MVP demonstrated in live exercises with Swedish Fire and Rescue Services, reusable integration patterns, and a validation method (KPIs, test scenarios, field methodology). Impact: faster, safer decisions under time pressure, lower cognitive load for incident command, a credible path for Swedish specialist vendors from components to interoperable system offerings, and a transferable architecture for industrial facilities, critical infrastructure, and urban resilience.
Planned approach and implementation
Running from M1 to M24, NaviGateAI is implemented through five linked work packages: WP1 management and dissemination; WP2 use cases, requirements, KPIs and architecture; WP3 perception and sensor fusion using wearables and drones; WP4 an LLM-based explainable recommendation engine; and WP5 UI/MVP integration. The work follows an iterative build-test-refine cycle, with repeated field exercises with Fire and Rescue Services to validate usability, robustness and operational value.