Ryan Barron

University of Maryland, Baltimore County, University of Maryland, Baltimore

Papers

Total Citations

H-Index

About

Ryan Barron is a researcher at the forefront of grounded language acquisition and human-robot interaction, with a particular focus on bridging the gap between virtual and physical environments. His work integrates natural language processing, computer vision, and signal processing to enable robots to learn language from multimodal sensory data, addressing critical challenges in sample efficiency and domain adaptation. Barron’s most cited paper, “A Spoken Language Dataset of Descriptions for Speech-Based Grounded Language Learning” (2021, 6 citations), introduces a multimodal RGB+depth dataset that serves as a foundational resource for training robots to understand spoken descriptions of objects and scenes. He further advances this line of inquiry through innovative use of virtual reality, as demonstrated in “Head Pose for Object Deixis in VR-Based Human-Robot Interaction” (2022, 3 citations) and “A Collaborative Building Task in VR Vs. Reality” (2024, 3 citations). In the former, he developed the Robot Interaction in VR simulator, leveraging VR to efficiently collect training data for deictic gestures and object referencing. Barron’s work is notable for its practical impact on deploying grounded language systems in real-world robotics, making him a key contributor to the future of intuitive human-robot collaboration.