Keegan W. Quigley

Keegan W. Quigley is an associate staff member of the Artificial Intelligence (AI) Technology Group. His research focuses on multimodal representation learning, knowledge-informed AI, and machine perception for autonomy. Currently, Quigley is working on improving automated chest X-ray diagnostics for clinical settings through the use of large language models, developing autonomous small uncrewed aerial system (sUAS) controls, and applying graph neural networks for AI-enhanced material design. He is interested in ways that we can constrain deep learning with prior domain knowledge and multimodal data sources, leading to more interpretable and explainable AI systems, especially for applications in healthcare and climate.

Quigley joined Lincoln Laboratory in 2018 after receiving his ScB degree in engineering physics from Brown University. He has also interned at NASA, where he researched algorithms for wildfire temperature retrieval from hyperspectral data. Prior to joining the AI group, his work at the Laboratory included development of spectral classification algorithms, UAS detection techniques, and various systems analysis efforts.