Stalker XE Block 25 UAV in flight
A Stalker XE Block 25 UAV was used in a test simulating multiple variations of fuel contingencies. Photo: Lockheed Martin

Lockheed Martin’s Skunk Works just ran a live test showing how artificial intelligence (AI) can take the wheel when unmanned missions hit a snag. 

The demo centered on an AI mission contingency management system that handled unexpected fuel issues on the Stalker XE Block 25 unmanned aerial vehicle (UAV) and an Alta X 2.0 drone modified by Drone Amplified.

Here’s what happened: the AI scanned the situation, generated re-plan options, and let the human operator pick the path. The Stalker returned to base, and the Alta X seamlessly picked up the reassigned mission with no micromanagement needed. 

“This demonstration proves AI can move from the lab to the battlefield, delivering a multitude of capabilities ranging from autonomous decision-making to rapid data flow between unmanned vehicles across air, ground and synthetic environments,” said OJ Sanchez, Vice President and General Manager of Lockheed Martin Skunk Works. 

How It Worked

The Stalker UAV fed its mission data into a unified command-and-control node that also managed an unmanned ground vehicle (UGV) in Kansas and UAVs provided by Fulcrum.

One mobile command system was juggling drones and robots — mounted, dismounted, and even below-the-noise — across separate locations, linking air and ground operations seamlessly.

The demo leaned on Lockheed’s STAR.SDK platform, part of the STAR.OS constellation, which connects the AI system to a chat-style interface for easy operator interaction. 

This setup lets multiple AI tools and unmanned platforms work together smoothly, keeping autonomous systems fast and in sync.

“By fusing AI‑enabled UAV replanning with UGV capabilities, we give warfighters the safety, speed and confidence they need to act first in contested environments,” Sanchez added. 

Meet the Drones

Lockheed’s Stalker XE can be hand‑launched using a bungee or rail, carries up to 5.5 pounds (2.5 kilograms) of payload, and tops out at 48 pounds (22 kilograms) in battery configuration or 44 pounds (20 kilograms) with a fuel cell.

It can fly for more than eight hours, reach altitudes of up to 12,000 feet (3,658 meters), and hit 58 miles (93 kilometers) per hour.

The Alta X 2.0, a modular evolution of Freefly Systems’ Alta X, can carry a wide range of payloads.

Flight times vary with load: 50 minutes empty, 30 minutes with a 5-kilogram (11-pound) Phoenix LiDAR sensor, 22 minutes with a 10-kilogram (22-pound) Movi Carbon gimbal, or 35 minutes with a 4-kilogram (8-pound) mapping camera.

You May Also Like

From Aerial to Maritime: Hivemind ‘AI Pilot’ Moves Into Taiwan’s Sea Drones

Taiwan is expanding AI-enabled maritime operations through autonomous vessel integration and live sea trials.

Pentagon Says AI Use Across US Military Jumped 1,775% in Just One Year

Pentagon officials say AI tools are rapidly spreading through military intelligence, logistics, and autonomous combat systems.

Lockheed to Develop AI Tools for DARPA’s Autonomous Air Combat Capability

DARPA teams up with Lockheed Martin to enhance BVR autonomy with AI tools and aircraft models, aiming for faster, smarter decisions in future air combat.

Odysight.ai Lands Defense Pilot Orders as AI Maintenance Gains Momentum

The goal? Show that AI can accurately spot early signs of wear or failure in combat settings to keep missions on track.