Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

Combating AI sensors on the battlefield: dynamic heat signature decoys for personnel and equipment (COMBAT-AI)

Reference number
Coordinator coXa carry AB
Funding from Vinnova SEK 1 682 940
Project duration November 2025 - November 2026
Status Ongoing
Venture Civil-military synergies
Call Needs-driven defense innovation in the Transparent Battlefield

Purpose and goal

The core of the project is the development of decoys based on graphene-coated textiles. The technology enables flexible, lightweight and dynamic heat signatures that can be adapted to different types of decoys and that can change in real time to deceive even AI-driven sensor systems. The project is carried out in collaboration between Grafren AB and Artik-Tech AB (a subsidiary of Coxa Carry), with extensive experience in product development for military applications.

Expected effects and result

Our technology can give our own units advantages such as lower vulnerability, spreading risk and getting inside the opponent´s decision loop. The risk of detection and our own losses is minimized. The technology and its use have never before been used on the battlefield. This gives us initial advantages on the battlefield, which in turn can provide the breathing space needed for important tactical actions and improved decision-making.

Planned approach and implementation

The project will be implemented by Coxa Carry/Artik-Tech AB (coordinator) and Grafren AB. The project activities are divided into five work packages that are evenly distributed between the parties. Work package 1 – Management, coordination and dissemination of results Work package 2 – Material selection and Egenskap Optimering Arbetspaket 3 – Design of heat-generating dummy targets Work package 4 – IR and functional Laboratorietester Arbetspaket 5 – Field tests

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 14 November 2025

Reference number 2025-03210