Rostec AI radar Sokol-08 detects and guides against drone swarms
Bottom line
Russian state corporation Rostec claims its new Sokol-08 radar uses AI to detect small UAVs and swarms, filter false positives, and guide interceptor drones.
Why it matters
Indicates Russian efforts to harden air defenses against drone swarms using AI-driven discrimination, potentially complicating NATO saturation tactics. Requires monitoring for field deployment and performance against complex multi-drone profiles.
Evidence — 1 independent origin
Original text (excerpt)
📡 Ростех запускает производство «умных» радаров для вывления массовых дроновых атак. Наш холдинг Росэл создал радиолокационную станцию «СОКОЛ-08» с алгоритмами машинного обучения. Мобильный комплекс способен выявлять малые БПЛА и рои дронов. Ключевые особенности системы: ▪️ 2D-фа
Related findings
- Rostec unveils Dan-T loitering munition with autonomous AI targeting · 8 Sep 2026 · B2
- Rostec delivers Zubr AD system and upgrades Yak-130 for counter-UAV roles · 22 Sep 2026 · D2
- Rostec presents 'Pauyna' modular drone protection system · 15 Oct 2026 · B3
- GU MO identifies 54 KRET enterprises under Rostec for drone/EW components · 15 Sep 2026 · C3
- Russian MoD claims high-accuracy drone strikes in zero-visibility fog · 4 Oct 2026 · B1
← Latest findings · All findings from August 2026
History · version 1 · first published · last substantive update
Cite this finding
Robot War (2026). Rostec AI radar Sokol-08 detects and guides against drone swarms. Hetzner OSINT, 28 August 2026. https://robotwar.io/osint-hetzner/2026-08-28--rostec-ai-radar-sokol-08-detects-and-guides-against-drone-swarms/
@misc{robotwar-2026-08-28--rostec-ai-radar-sokol-08-detects-and-guides-against-drone-swarms,
title = {Rostec AI radar Sokol-08 detects and guides against drone swarms},
author = {Robot War},
howpublished = {\url{https://robotwar.io/osint-hetzner/2026-08-28--rostec-ai-radar-sokol-08-detects-and-guides-against-drone-swarms/}},
year = {2026},
note = {Hetzner OSINT finding D4}
}Grades: source reliability A–F from the channel register; information credibility 1–6 from independent origins — reposts count once. The bottom line and summary are written by the model from the cited posts; grades and source roles are rule-based. Methodology 2026-10-15.v6 · Corrections · JSON · RSS · API performance