Artificial Intelligence’s Dogfight with Human Pilot: DARPA’s Air Combat Evolution Program Puts Machine Learning to the Test in High-Altitude Aerial Combat Trials

In September, an F-16 fighter controlled by artificial intelligence (AI) engaged in a dogfight with another F-16 piloted by humans at the US Air Force Test Pilot Training School at Edwards Air Force Base. This exercise was part of the US Defense Advanced Research Projects Agency (DARPA) Air Combat Evolution (ACE) program, aimed at developing automated control systems with capabilities equivalent to human pilots.

The X-62A, also known as the In-Flight Simulation Test Aircraft (VISTA), is based on Lockheed Martin’s F-16D fighter and has been equipped with a Block 40 avionics system and various modifications for AI integration. The goal of the program is to use machine learning to replace humans in controlling aircraft, especially in complex and unpredictable situations like aerial combat.

However, despite AI controlling the X-62A, there is always a pilot present in the cockpit for safety. Aerial combat trials conducted at high altitudes and speeds require strict safety regulations to prevent accidents and chaos. The ACE program aims to regulate AI, establish ethical guidelines for its use, and study human trust in AI. Successful implementation of ACE could lead to AI systems taking over pilot roles in combat and allowing pilots to focus on more strategic aspects of missions.

DARPA is working towards creating AI systems that can enhance aerial combat capabilities and potentially change the dynamics of air warfare through ongoing trials and developments. Through the ACE program, DARPA aims to push the boundaries of technology and explore new possibilities in aviation.