Jump to content

DARPA AlphaDogfight

Edit links
From Wikipedia, the free encyclopedia
Dogfight between 2 F-16s in simulation software; the pilots in this case are AI programs who are fighting for the chance to engage with a human pilot. The trajectories of the aircraft are denoted in pink and blue, as are the scores of the engagements.

The DARPA AlphaDogfight was a 2019–2020 DARPA program that pitted computers using F-16 flight simulators against one another. The computers were managed by eight teams of humans, who competed in a single-round elimination for the right to battle a skilled human dogfighter. Heron Systems corporation wrote a deep reinforcement learning software tool that bested the human pilot by a score of 5–0.[1] The tournament program was managed by the Applied Physics Laboratory.[2] The trials took place in October 2019 and January 2020 while the finals were held in August 2020.[2][3] In 2024 a successor version of the program was tested with in the physical world with the X-62A.[4]

References

[edit]
  1. ^ Cogley, Michael (21 August 2020). "AI defeats human F-16 pilot in virtual dogfight". Telegraph Media Group Limited.
  2. ^ a b "AlphaDogfight Trials Foreshadow Future of Human-Machine Symbiosis". DARPA. Retrieved 2020-10-30.
  3. ^ DARPAtv (26 Aug 2020) AlphaDogfight trials, final event video 5:07:15 — 4:39:53 is start of AI versus human event
  4. ^ Koller, Chase (2024-04-17). "USAF Test Pilot School and DARPA announce breakthrough in aerospace machine learning".


Stub icon

This artificial intelligence-related article is a stub. You can help Wikipedia by expanding it.

Retrieved from "https://en.wikipedia.org/w/index.php?title=DARPA_AlphaDogfight&oldid=1255608921"