Lockheed Martin and University of Iowa‘s Operator Performance Laboratory (OPL) demonstrate AI-powered coordination between crewed and uncrewed aircraft for future combat missions. An execution of electronic attack task by AI agents shows how autonomous uncrewed aerial systems can operate in coordination with crewed tactical platforms in future combat operations, creating a unified team to address complex threats.
This project named Enhanced Collaborative High-Frequency Orientation System (ECHOS), was sponsored by Lockheed Martin’s 21st Century Security Demonstrations & Prototypes (D&P) organisation. “ECHOS is a terrific example of using artificial intelligence and UAS to further enable the DOD vision of Joint All Domain Operations (JADO), providing new capabilities to identify targets and deliver effects,” says Joe Villani, Lockheed Martin D&P vice president.
These L-29s were flown by experienced OPL pilots, following instructions from AI agents in a form of heading, altitude and speed cues. Demonstrating how AI can provide data for decision making and increased mission productiveness by reducing pilot workload. Pilots maintained an option to stop following AI cues if at any point they felt unsafe, or the agent tried to go outside acceptable operating conditions.
“This was an awesome experience, and the event went smoothly. It was an exceptional example of industry and academia working together on a cutting-edge project. We’re excited to take this to the next level,” says Tom “Mach” Schnell, OPL founder and director.
AI agents were trained using advanced deep multi-agent reinforcement learning techniques, incentivising rising collaborative tactics. There is minimal reward shaping on these agents, emphasising mission completion. Agents were able to learn these tactics with sparse rewards, ensuring better possible tactics for mission were executed.
This demonstration focused on sim-to-real transfer to train an AI agent in a simulated environment, fly it on real aircraft and test its behaviour. These tests demonstrated that AI agents can be believable to deliver high performance and secure behaviours. Throughout day one of testing, agents were aligned between fighter and target within a very tight tolerance, never allowing radar to get a track on fighter. Team completed all test cards in three days of testing.
By year end of 2023, Skunk Works and OPL team will test AI in an end-to-end suppression and destruction of enemy air defenses (SEAD/DEAD) mission. Lessons learned will inform follow-on AI/autonomy development in support of future programmes such as the Air Force’s collaborative combat aircraft (CCA), as well as ongoing crewed-uncrewed teaming development. This work furthers Lockheed Martin’s 21st century security vision to deliver integrated, mission-focused capabilities with speed and productivity to keep forces and allies always ready.
Follow us and Comment on Twitter @TheEE_io