The demonstration used the Stalker UAV as the primary asset and the Alta X as a secondary platform to receive reassigned tasks when the AI detected a fuel-related constraint.
During the event, the team generated several fuel contingency scenarios and fed them into a ground command and control system equipped with an AI agent.
Within seconds, that system assessed the situation, produced alternative mission plans, and presented them to the human operator, who then selected a preferred course of action while the AI executed the changes.
Once the operator confirmed a replanning option, the AI shifted the Stalker's remaining mission tasks to the Alta X and instructed the Stalker to return to base.
The process allowed the operator to resolve the contingency while continuing to monitor other mission responsibilities, illustrating how AI can manage time-critical reallocation of unmanned assets.
The Stalker platform also fed its mission data into a unified command-and-control node that simultaneously managed an unmanned ground vehicle operating in Kansas, supported by additional UAVs supplied by Fulcrum.
This setup demonstrated control of air and ground unmanned systems from a single mobile node and showed that the node could direct multiple drone meshes dispersed across different locations and operating in mounted, dismounted and below-the-noise configurations.
"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, Lockheed Martin Skunk Works.
"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."
The trial also incorporated Lockheed Martin's STAR.SDK toolset, which is part of the company's STAR.OS AI integration framework.
STAR.SDK provided the link between the contingency-management application and a user interface, allowing operators to use a chat assistant to request and review mission retasking options.
The STAR.OS architecture is designed to let multiple AI applications and services operate together across different unmanned systems.
In this demonstration, it enabled the contingency-management agent, the operator interface, and the various unmanned platforms to exchange data and commands as a coordinated system.
Related Links
Lockheed Martin
UAV News - Suppliers and Technology
| Subscribe Free To Our Daily Newsletters |
| Subscribe Free To Our Daily Newsletters |
