Skip to main content
  1. Home
  2. Emerging Tech
  3. News

Drone dogfight shows what happens when unmanned swarms collide

Add as a preferred source on Google

Two drone swarms took to the skies above a National Guard facility in California earlier this year to study the future of aerial warfare. No shots were fired, but the friendly dogfight gave researchers the first data on live engagement combat between groups of autonomous unmanned aerial vehicles (UAVs).

“The ability to engage a swarm of threat UAVs with another autonomous swarm is an area of critical research for defense applications,” Don Davis, division chief of the robotics and autonomous systems branch of the Georgia Tech Research Institute, said in a press release. “This experiment demonstrated the advances made in collaborative autonomy and the ability of a team of unmanned vehicles to execute complex missions. This encounter will serve to advance and inform future efforts in developing autonomous vehicle capabilities.”

Recommended Videos

The teams each attempted to launch 10 drones, but two drones failed to take off, so the dogfight was uneven. Though the drones were identical in form, the algorithms that controlled the aircraft differed, allowing them to fly in varying formations and test a number of tactics.

“Both teams were trying to solve the same problem of flying a large swarm in a meaningful mission, and we came up with solutions that were similar in some ways and different in others,” said Charles Pippin, a senior research scientist at the Georgia Tech Research Institute. “By comparing how well each approach worked in the air, we were able to compare strategies and tactics on platforms capable of the same flight dynamics.”

Before taking the drones out for a live engagement, the researchers tested their algorithms in a series of rapid simulations that helped determine the most effective tactics. The researchers hope their tests will help identify how aerial battles might best be fought in the future.

“Autonomous techniques using machine learning may identify new tactics that a human would never think of,” Davis said. “Humans tend to base their techniques on tactics that manned fighters have used in the past. These autonomous aircraft may invoke new strategies.”

Dyllan Furness
Former Contributor
Dyllan Furness is a freelance writer from Florida. He covers strange science and emerging tech for Digital Trends, focusing…
Claude can now join your Slack channels and work alongside your team
Laptop running Claude Fable

For years, AI assistants have been siloed. You open ChatGPT, Claude, Gemini, or Copilot, type a prompt, get an answer, and move on. Anthropic's new Claude Tag feature takes a different approach. Instead of making employees jump into a separate AI chat every time they need help, it brings Claude directly to where many teams already spend their day: Slack.

Add Claude to a channel, grant it access to needed tools, and tag @Claude for help — whether analyzing data, writing reports, reviewing code, or investigating incidents. But Claude Tag isn't just another chatbot integration. Its key differentiator is that Anthropic positions it as a digital coworker for your team, enabling seamless collaboration where multiple users can jointly interact with the same AI within their work environment.

Read more
Getty Images accused AI of wholesale theft. It’s now an official ChatGPT image partner.
Advertisement, Shop, Clothing

The AI industry's most fascinating stories often come from unlikely alliances, and this is certainly one of them. Getty Images, a company that has spent years raising concerns about how AI models are trained and how creative work is used, is now officially partnering with OpenAI.

The new agreement will allow Getty Images' licensed content to appear across ChatGPT's search and discovery experiences. That means users may begin seeing Getty's professionally licensed photos and visual assets integrated into ChatGPT responses, adding more visual context to searches and AI-generated answers. Getty says the goal is to make AI-powered search more useful and trustworthy by relying on high-quality, licensed content rather than the murky sourcing practices that have sparked countless debates across the AI industry.

Read more
Timekettle’s new X1 Meeting Hub does real-time translation for 50 people and fits in your pocket
Fifty participants, five languages, one 199-gram hub, and no booth required.
Electronics, Screen, Computer Hardware

Professional conference interpretation setups are notoriously painful. Dedicated booths, trained interpreters, bulky hardware, and a bill at the end of every month that makes you rethink whether the meeting was even required in the first place. 

Timekettle wants to collapse all of that into a single hub that weighs 199 grams (less than modern flagship smartphones). The company just launched the X1 Meeting Interpreter Hub. 

Read more