Max Robotics — Global Service Robot Directory + US Certification

About

Matthew Pan is a leading researcher at the intersection of robotics, human-robot interaction, and computer vision, with a focus on enabling robots to understand and replicate human behavior. His major contributions span three key areas: humanoid motion retargeting, active visual search, and the characterization of emerging sensing technologies. Pan’s most cited work, “Nonparametric Motion Retargeting for Humanoid Robots on Shared Latent Space” (2020, 21 citations), introduces a semi-supervised learning method that transfers human motion data to humanoid robots while ensuring the feasibility of the resulting robot motions—a critical step toward more natural robot movement. In “Zero-shot Active Visual Search (ZAVIS)” (2023, 12 citations), he tackles the challenge of enabling mobile robots to locate objects described in free-form text, breaking away from predefined search sets. More recently, Pan’s “Robotic Characterization of Markerless Hand-Tracking on Meta Quest Pro and Quest 3” (2025, 9 citations) provides the first systematic, robotic evaluation of hand-tracking accuracy on commercial VR headsets, offering vital insights for immersive interaction. His work “Towards Embedding Dynamic Personas in Interactive Robots” (2024, 3 citations) extends persona-driven dialog agents into physical robots, enhancing audience engagement. With a growing citation record and a clear trajectory from foundational motion transfer to applied human-robot interaction, Pan is shaping how robots perceive, move, and interact with people.