Lethal AI: Rafael unveiled Deep-Learning Target Recognition
16 June, 2019
Using advanced AI and deep-learning technologies, SPICE-250 learns the specific target characteristics ahead of the strike, for pinpoint accuracy hit
Photo above: SPICE-250 under the wings of F-16
Rafael Advanced Defense Systems announced that it has successfully tested and demonstrated a new Automatic Target Recognition capability for its SPICE-250 air-to-surface munition. The newly-unveiled ATR feature is a technological breakthrough, enabling SPICE-250 to learn the specific target characteristics ahead of the strike, using advanced AI and deep-learning technologies.
During flight, the pilot selects the target type to be attacked and allocates a target to each weapon. The weapons are launched towards the vicinity of the targets, using their INS for initial navigation. When approaching the target area, the weapons use the ATR mode for detection and recognition of the targets. Each weapon homes-in on the pre-defined target, either autonomously or with a human-in-the-loop, aided by the ATR algorithm.
SPICE (250, 1000, 2000) is a family of autonomous, air-to-ground weapon systems that attack targets with pinpoint accuracy without depending on GPS navigation in GPS-denied environments. It has a standoff range of 100 kilometers, and can be equipped with either general purpose or penetration 75kg class warhead. SPICE-250 uses a common aircraft interface and Smart Quad Rack (SQR) which simplifies the effort needed for aircraft integration. Four SPICE-250 weapons are carried on each SQR. SPICE is combat-proven with the Israeli Air Force and in operational service with a number of international customers.
Elbit Announced Deep Learning Photography Pod
AI is gradually become a reality in the modern battlefield. This week, Elbit Systems launched its CONDOR MS, a new Long Range Oblique Photography (LOROP) system that introduces Multi-Spectral (MS) sensing capability and Artificial Intelligence (AI) analytics to stand-off strategic intelligence gathering missions. CONDOR MS integrates three high resolution Electro Optic (EO) sensors into the Company’s certified and widely operational CONDOR2 system: Visible & Near Infra-Red (VNIR), Medium-Wave Infrared (MWIR), and Short-Wave Infrared (SWIR).
Elbit said in a press release that this unique combination extends coverage area in day, night and adverse weather conditions. Deep learning algorithms and precise geo-location enable the CONDOR MS to identify a large number of targets at extremely high rates.The CONDOR family of systems is integrated onboard a variety of platforms. Among them the F-16 A/B/C/D/I, F-4, SU-30 as well as B-737.