Max Robotics — Global Service Robot Directory + US Certification

About

Kyungdon Joo is a roboticist whose work spans humanoid control, 3D perception, and collaborative SLAM, with a focus on enabling robots to operate reliably in complex, real-world environments. He was a key member of Team KAIST during the DARPA Robotics Challenge (DRC) Finals, where his contributions to the robot system and control strategy of DRC-HUBO+ were documented in a highly cited 2016 paper (127 citations). That work demonstrated how a humanoid robot could perform disaster-response tasks under degraded communication, including driving and egressing a utility vehicle—a capability detailed in his 2015 paper. More recently, Joo has advanced 3D perception for autonomous navigation. His 2023 paper on learning-based reflection-aware virtual point removal tackles the challenge of LiDAR artifacts on reflective surfaces, improving large-scale point cloud accuracy. He also introduced the “San Francisco World” model (2024), a novel structural model that leverages urban slope regularities for 3-DoF visual compassing, enabling 3D inter-floor navigation. Additionally, he contributed a benchmark dataset for collaborative SLAM in service environments, supporting multi-robot coordination indoors. With over 150 citations, Joo’s work bridges robust hardware control and intelligent perception, pushing robots from labs into unstructured, human-centric spaces.