The AlphaDogfight Trials is a virtual competition designed to demonstrate advanced artificial intelligence (AI) algorithms that can perform simulated within-visual-range air combat maneuvering. The first two trials took place November 2019 and January 2020 near Baltimore at the Johns Hopkins University Applied Physics Laboratory, in which teams pit their AIs against DARPA-provided adversarial “Red” AIs in a series of one-versus-one dogfights.
The third and final competition will take place virtually August 18-20. Participating teams and audience members will watch online as AI algorithms control simulated F-16 fighters in aerial combat, culminating in a matchup on August 20 between the top AI and an experienced Air Force fighter pilot flying a virtual reality F-16 simulator.
“We weren’t able to host the finals at AFWERX in Las Vegas as we’d originally planned with fighter pilots from the Air Force Weapons School at nearby Nellis Air Force Base,” says Col. Dan “Animal” Javorsek, program manager in DARPA’s Strategic Technology Office. “We are still excited to see how the AI algorithms perform against each other as well as a Weapons School-trained human and hope that fighter pilots from across the Air Force, Navy, and Marine Corps, as well as military leaders and members of the AI tech community will register and watch online. It’s been amazing to see how far the teams have advanced AI for autonomous dogfighting in less than a year.”
Eight teams were selected last year to compete in the trials, which are designed to demonstrate advanced AI algorithms capable of performing simulated within-visual-range air combat maneuvering = colloquially known as a dogfight. The series of trials were designed to energize and expand a base of AI developers for DARPA’s Air Combat Evolution (ACE) program, which seeks to automate air-to-air combat and build human trust in AI as a step toward improved human-machine teaming.
The three-day event will be streamed live from the Johns Hopkins Applied Physics Laboratory (APL) in Laurel, Maryland, via a ZoomGov webinar featuring multiple “channels.” Dubbed AlphaDogfight Trials TV (ADT TV), this multi-view format will afford viewers comprehensive perspectives of the dogfights in real-time and feature experts and guests from the Control Zone, akin to a TV sports commentary desk.
Each day of Trial 3 will have a different focus with activities broadcast throughout the day on ADT TV:
- Day 1 features each of the eight teams flying their algorithms against five APL-developed adversary AI algorithms.
- On Day 2, teams fly against each other in a round-robin tournament.
- On Day 3, the top four teams compete in a single-elimination tournament for the AlphaDogfight Trials Championship. The champion team then flies against an F-16 pilot to test the AI’s abilities against a human.
“Prime time” viewing will take place between 1:30 and 3:30 p.m. EDT on Day 3, Aug. 20, with remarks from Javorsek and other DARPA officials, recaps of the previous days’ activities and scores, and the final human vs AI dogfight.
“Regardless of whether the human or machine wins the final dogfight,” says Javorsek, “the AlphaDogfight Trials is all about increasing trust in AI. If the champion AI earns the respect of an F-16 pilot, we’ll have come one step closer to achieving effective human-machine teaming in air combat, which is the goal of the ACE program.”
Registration to watch the AlphaDogfight Trials is now open at https://events.jhuapl.edu/ADT3AUGUST2020.