Artificial Intelligence Capabilities Enhance Reliability of Sensors

Employing artificial intelligence (AI) to make sensors more reliable in challenging environments is a development that could greatly benefit those guiding missions for the Air or Space Force.

It’s a technology currently being advanced by Dr. Vanessa Chen, an associate professor in the Department of Electrical and Computer Engineering at Carnegie Mellon University (CMU).

“The innovation leverages reinforcement learning applied to a multimodal learning sensor system to enable feedback control for self-healing and performance optimization in dynamic environments,” Dr. Chen said “The system continuously monitors multiple sensing modalities such as EO/IR (Electro-Optical and Infrared), Radar and LiDAR (Light Detection and Ranging), and applies adaptive learning to reconfigure and restore functionality when disruptions occur, ensuring resilient and efficient operation in harsh conditions.”

Essentially, artificial intelligence would increase the reliability of sensors in harsh conditions by automatically fixing problems and improving performance when things go wrong.

“The concept is that conventional radar design typically depends on the software-defined radio's processing speed,” Dr. Chen said. “All the front-end components would be on one chip, and the digital processor would be on another. The interface becomes a bottleneck. For our applications, like UAVs (unmanned aerial vehicles) or airplanes, you need fast processing of the received signal to track objects because the velocity is pretty high.

“We're trying to overcome that bottleneck by fully integrating the signal data conversion and the digital accelerator into the radar front end. This also facilitates feedback control when environmental conditions change. For example, if it's raining or foggy, the machine learning accelerator can control the smart antenna over the radar front end. That's what we're trying to implement for this project.”

It’s a fundamentally important upgrade, especially when it comes to safety.

“The motivation stems from the urgent need for trusted and reliable sensing and computing at the edge, particularly for Air Force and Space Force missions where systems must continue to function despite environmental stresses, adversarial interference or hardware degradation,” Dr. Chen said. “By embedding reinforcement learning accelerators for adaptive recovery and optimization, the technology helps extend mission capability, survivability and operational effectiveness.”

For Dr. Chen, who received her Ph.D. in electrical and computer engineering from Carnegie Mellon in 2013, much of the work she’s done in the past has played a part in this breakthrough.

“My research background centers on developing resilient electronics and intelligent sensing systems for extreme and dynamic environments,” she said. “I have worked extensively on embedded machine learning, reinforcement learning for self-healing circuits and systems, and multimodal sensor integration for autonomous systems. These experiences shaped my approach to designing solutions that adapt in real time to environmental changes and system-level degradation.”

The CMU professor’s work caught the eye of the Air Force Research Lab (AFRL) when she submitted her idea through the Tech Connect website. More specifically, Dr. Robert Ewing, the director of the Center for Innovative Radar Engineering at the AFRL, took notice.

“Dr. Vanessa Chen is helping us to collaborate and incorporate novel technical insights for both hardware and software to make this possible with academics and industry,” Dr. Ewing said. “The focus is on RF/EO (radio frequency/electro-optical) imaging for ATR (automatic target recognition), and exploring how feedback-driven, self-healing processing techniques can be adapted to support these needs.

“Think of the famous movie “Déjà Vu” (2006), where the technology could move to direct locations in real-time for 3D imaging from the data collections in a specific region with scalable resolution, this is the focus of the endgame for EO/RF imaging for the warfighter.”

The Tech Connect experience has been a productive one for Dr. Chen.

“My expectation was that the platform would help connect me with the right technical community and provide feedback on the alignment of my idea with Air Force and Space Force needs,” she said. “These expectations were met, as the feedback was timely and insightful.

“They helped contextualize my idea within ongoing research challenges and suggested potential applications I had not initially considered.”

The collaboration has been beneficial for both parties, and Dr. Chen sees a bright future for the technology.

“The next step is to transition from proof-of-concept prototypes toward demonstrations on deployed platforms, including UAVs and space systems,” she said. “I see the technology evolving into a modular framework that can be integrated with diverse sensor architectures, offering both autonomy and resilience for mission-critical operations. Over time, it could support self-optimizing sensor networks, enabling long-duration operations with minimal human intervention.”

About AFRL

The Air Force Research Laboratory, or AFRL, is the primary scientific research and development center for the Department of the Air Force. AFRL plays an integral role in leading the discovery, development and integration of affordable warfighting technologies for our air, space and cyberspace force. With a workforce of more than 12,500 across nine technology areas and 40 other operations across the globe, AFRL provides a diverse portfolio of science and technology ranging from fundamental to advanced research and technology development. For more information, visit www.afresearchlab.com.

About Air Force and Space Force Tech Connect

The Air Force and Space Force Tech Connect website provides access to current, open opportunities, meet-up events, other Department of the Air Force science and technology enterprise connectors and a way for anyone to share an idea. The Tech Connect team, comprised of AFRL personnel, connects quality, relevant ideas/technologies with Department of the Air Force subject matter experts. The team will review ideas/inquiries, provide feedback on innovative ideas and establish a dialogue with potentially interested Air Force and Space Force programs. For more information, visit: https://airforcetechconnect.org/.