Challenges and Progress in Predictive Maintenance of Long-Endurance & Long-Range Uncrewed Platforms

Kenneth Lu, Sanja Cvijic, Arjuna Balasuriya

AUVSI XPONENTIAL 2024, San Diego, CA (April 2024)

Today’s uncrewed platforms are typically operated by humans using remote control to guide every detailed aspect of a mission. However, as missions become more complex, there are many scenarios (particularly in the marine and ground domains) in which operators are unable to communicate with these uncrewed platforms in real time (due to adverse environmental conditions, regulatory restrictions on communications in ecologically sensitive areas, active interference by adversaries, or the desire to remain covert), making it challenging to know the health and status of the platform, and to recalibrate and update mission and control parameters on the fly. This becomes challenging especially when the uncrewed platforms are deployed for long-endurance and long-range missions. Fortunately, significant technical advances in onboard computing power and enhanced sensors offer a pathway to a level of autonomy that can overcome such communications limitations. Predictive maintenance algorithms and digital twins of health and status are becoming essential in preventing unexpected failure and extending the lifespan of uncrewed platforms.

In this paper, we present insights into the importance of predictive maintenance and provide examples of implementation of predictive maintenance in uncrewed platforms such as robotic com-bat vehicles (RCVs). Moreover, we will discuss how hybrid artificial intelligence (Hybrid-AI) techniques rooted in probabilistic models serve as a foundation for predicting health and status of un-crewed platforms.

For More Information

To learn more or request a copy of a paper (if available), contact Kenneth Lu.

(Please include your name, address, organization, and the paper reference. Requests without this information will not be honored.)