Next capture attempts scheduled to occur in spring of 2021

Like.

Comment.

Attempts at airborne retrieval of three unmanned air vehicles, nicknamed Gremlins, were just inches from success in DARPA’s latest flight test series that started on October 28. Each X-61A Gremlins Air Vehicle (GAV) flew for more than two hours, successfully validating all autonomous formation flying positions and safety features. Nine attempts were made at mechanical engagement of the GAVs to the docking bullet extended from a C-130 aircraft, but relative movement was more dynamic than expected and each GAV ultimately, safely parachuted to the ground.

Multi-domain operations, the Army’s future operating concept, requires autonomous agents with learning components to operate alongside the warfighter. New Army research reduces the unpredictability of current training reinforcement learning policies so that they are more practically applicable to physical systems, especially ground robots.

These learning components will permit autonomous agents to reason and adapt to changing battlefield conditions, said Army researcher Dr. Alec Koppel from the U.S. Army Combat Capabilities Development Command, now known as DEVCOM, Army Research Laboratory.

The underlying adaptation and re-planning mechanism consists of reinforcement learning-based policies. Making these policies efficiently obtainable is critical to making the MDO operating concept a reality, he said.