The UK Defence Science and Technology Laboratory (DSTL) has teamed up with industry partners to trial AI recognition technologies at Salisbury Plain.
As part of the test, various mobility assets were deployed at five site areas, including infantry vehicles, armored personnel carriers, and tanks.
Developers from Leonardo, Thales, MBDA, Frazer-Nash, and Lockheed Martin then recorded data from different sensors and cameras to train machine-learning algorithms in realistic terrains, camouflage, obscurants, and the movement of vehicles.
The demonstration validated algorithms that support AI-based capabilities and weapons with cost-effectiveness.
Furthermore, it addressed the current lack of datasets for tactical target recognition. According to DSTL, this is among the principal challenges for defense suppliers.
We worked with industry partners to record data from a range military vehicles
— Dstl (@dstlmod) December 2, 2022
Improving Combat Decisions
According to the UK Ministry of Defence, DSTL will utilize the data to further develop investigation and target acquisition methods supporting the government’s Weapons Program and Cooperative Strike Weapons Technology Demonstrator program.
The datasets will also be stored in the ministry-owned military image library and shared across the UK defense community to further enhance AI techniques.
“The trial drew on the specialist expertise across multiple areas of DSTL, bringing them together to collaborate with industry partners and government colleagues,” DSTL Weapon Systems Program Manager Simon Zavad explained.
“The data gathered could accelerate the development of AI software, improving the accuracy of data to enable commanders to make better combat decisions.”