{
  "id": 19984899,
  "title": "The Pentagon is testing war robots that can hunt in packs without GPS and find battlefield targets on their own. Humans still call the shots.",
  "url": "https://urgent.news/2026/11/14/the-pentagon-is-testing-war-robots-that-can-hunt-in-packs-without-gps",
  "topic": "world",
  "section": "World",
  "published": "2026-11-14T13:36:01.000Z",
  "source": {
    "name": "Business Insider",
    "slug": "business-insider",
    "url": "https://www.businessinsider.com/darpa-tested-autonomous-ground-robots-finding-enemy-targets-no-gps-2026-11"
  },
  "original_language": "en",
  "account": "The Pentagon is investigating robotic systems that can operate independently in GPS-denied conditions, mapping out terrain and identifying enemy targets without human intervention. DARPA, the Pentagon's research agency, conducted tests with autonomous ground vehicles (UGVs) during a field exercise at Fort Knox, Kentucky. These robots were capable of driving, mapping their environment, and locating potential threats, all while keeping a human operator in the loop to make strategic decisions.\n\nJason Gregory, a technical advisor at DARPA, explained that the goal is to place advanced sensors and equipment closer to the battlefield while keeping the operators safe and informed. The UGVs could work independently or collaboratively, depending on the mission requirements. During the Fort Knox exercise, one robot identified a closed box containing a drone and signaled the human operator, who then decided to launch a simulated rocket attack.\n\nThe RACER (Robotic Autonomy in Complex Environments with Resiliency) program, led by DARPA, focused on developing software that allows ground vehicles to rely solely on onboard sensors for navigation and decision-making, even if GPS signals are unavailable or compromised. This software was tested on both four-wheel and tracked UGVs to ensure compatibility across different hardware platforms.\n\nThe military's interest in autonomous ground robots stems from the need to operate effectively in contested or denied environments where GPS signals may be unreliable. DARPA's research drew on lessons learned from Russia's ongoing war in Ukraine, observing how their forces integrate ground robots into their operations. The challenges faced by autonomous UGVs vary depending on the terrain and environmental conditions, ranging from desert sand and rocks to swamps, forests, and snow-covered landscapes.\n\nDARPA's work on this program has involved five years of research into autonomy, artificial intelligence algorithms, and ground mobility, drawing on observations from the conflict in Ukraine. The lessons learned from the RACER program offer valuable insights for the broader US military, including the importance of maintaining human oversight and control over robotic systems, even as they become more autonomous. These findings will be shared with industry partners to further advance the development of unmanned systems for military applications.",
  "summary": "Once the uncrewed ground vehicles located targets without GPS navigation, the human operator decided the next steps.",
  "key_points": [
    "Pentagon testing autonomous robots for GPS-denied environments",
    "DARPA conducts field exercises at Fort Knox, Kentucky",
    "Robots can identify targets and signal human operators for strikes"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}