WhatsNew2Day
Latest News And Breaking Headlines

Military researchers are starting a new project to develop an AI drone based on the behavior of video players

Scientists build AI to control swarms of up to 250 drones using data from how people play video games such as StarCraft and Company of Heroes

  • Scientists from the University of Buffalo will develop an AI to control large drone swarms
  • The AI ​​is based on data collected from video game players
  • The team uses game data about tactical decisions and biometric data
  • Players used in the project play StarCraft, Company of Heroes and Stellaris

Researchers at the University of Buffalo have received a $ 316,000 grant from the Defense Advanced Research Projects Agency (DARPA), an agency funded by the US Department of Defense, to develop an artificial intelligence capable of control swarms of up to 250 drones.

To create the experimental AI, scientists from the University’s Artificial Intelligence Institute study video game players as they control autonomous swarms of digital military units in real-time strategy games such as StarCraft, Stellaris and Company of Heroes.

The team collects data about how players respond to a wide range of different tactical challenges and how they respond to unexpected changes in the terrain or battle conditions.

Researchers from the Artificial Intelligence Institute of the University of Buffalo will study the way video game players make choices in real-time strategy games such as StarCraft and Company of Heroes to develop an AI that can control swarms of up to 250 drones

Researchers from the Artificial Intelligence Institute of the University of Buffalo will study the way video game players make choices in real-time strategy games such as StarCraft and Company of Heroes to develop an AI that can control swarms of up to 250 drones

“We don’t want the AI ​​system to mimic only human behavior; we want it to be a deeper understanding of what motivates human actions, “said Souma Chowdhury of the University of Buffalo news site.

“That’s what will lead to more advanced AI.”

The team also collects a series of biometric data from the players, via eye tracking software and electro-encephalograms, which track brain activity during play.

The team hopes that by combining game decision data with real-time biometric feedback that gives hints about the player’s emotional and cognitive, large groups of drones can help coordinate complex tasks independently.

Think of exploring an area to make a 3D map, maintaining a security perimeter around certain locations and sending a group of drones to search for specific targets on unexplored terrain.

The team records in-game data about tactical choices players make, and collects biometric data about eye movements and brain wave activity

The team records in-game data about tactical choices players make, and collects biometric data about eye movements and brain wave activity

The team records in-game data about tactical choices players make, and collects biometric data about eye movements and brain wave activity

The research will be supported by a $ 316,000 grant from DARPA, which has recently begun to expand its efforts to build autonomous tools for controlling drone swarms

The research will be supported by a $ 316,000 grant from DARPA, which has recently begun to expand its efforts to build autonomous tools for controlling drone swarms

The research will be supported by a $ 316,000 grant from DARPA, which has recently begun to expand its efforts to build autonomous tools for controlling drone swarms

“The idea is to eventually scale up to 250 air and ground robots that work in very complex situations,” Chowdhury said.

“For example, there may be a sudden loss of vision due to smoke during an emergency. The robots must be able to communicate effectively and adapt to such challenges. ”

DARPA has tested its own internal program for controlling large groups of drones, called Offensive Swarm-Enabled Tactics (OFFSET).

In January, DARPA completed tests at a training facility in Hattiesburg, Mississppi, which showed a mix of drones and autonomous ground vehicles that worked together to create a map of the simulated battlefield while specific targets were found in the test facility, represented by QR codes.

While the drones were operating independently, human observers were able to track their movements and record map data as they were collected by the drones’ built-in cameras and lidar sensors.

DARPA plans to perform three more similar tests with its drone swarm technology over the next 18 months.

HOW FRANCE CATCHES UNWANTED DRONES

France has designed its own weapon against the growing threat of rogue drones buzzing through the air of their country: another drone, with a net.

Last year during a demonstration flight in La Queue-en-Brie, east of Paris, the mesh-flying machine was shown that snared a DJI Phantom 2 drone.

For months, France has been confronted with dozens of drone flights over sensitive locations – mostly nuclear facilities, a worrying development in a country that gets the highest percentage of its energy in the world from nuclear energy.

French authorities say that the drones are not currently a threat. But some fear that the drones can spy on French technology or one day be equipped with bombs or other weapons. Authorities have stepped up security at French nuclear sites and are investigating who might be behind the drone flights.

The potential risks of rogue states are terrorism, invasion of privacy, theft of trade secrets, and “damage to the credibility of government agencies, institutions or companies,” according to the French national research agency.

.