Scott Thomas

University of Maryland, College Park, United States Naval Research Laboratory

Papers

Total Citations

H-Index

About

Scott Thomas is a pioneering researcher in human-robot interaction, with a particular focus on multimodal interfaces, cognitive modeling, and collaborative robotics. His most influential work, "Using Vision, Acoustics, and Natural Language for Disambiguation" (2007), has garnered 36 citations and represents a landmark contribution to the challenge of building robust human-robot communication systems that integrate multiple sensory modalities — including vision, speech recognition, and natural language processing — to overcome the limitations of any single input channel. Thomas has also made significant strides in space robotics, collaborating with NASA to explore how humanoid robots can work alongside astronauts in ways that feel natural and intuitive, as reflected in his 2005 paper "Collaborating with Humanoid Robots in Space." His broader research agenda is deeply rooted in embodied cognition, investigating how placing computational cognitive models within physical robotic systems can yield richer, more adaptive behavior. His work on multimodal cooperation and collaboration further demonstrates his commitment to integrating speech, gesture, spatial reasoning, and human cognitive models into seamless human-robot partnerships. Thomas's research has meaningfully advanced the field's understanding of how robots can become genuine collaborative partners in complex, real-world environments.