Max Robotics — Global Service Robot Directory + US Certification

About

Sewoong Oh is a researcher whose work spans two distinct and impactful domains: robust meta-learning for data-scarce environments and the development of advanced mobile robotics for rough terrain. In machine learning, Oh has tackled the critical challenge of learning from many tasks where each task provides only a small number of labeled examples—a common bottleneck in fields like medical image processing and robotic interaction. His work on robust meta-learning for mixed linear regression with small batches (2020, 6 citations) proposes methods to exploit task similarities to enable effective learning even when isolated training is infeasible. In robotics, Oh has made significant contributions to the design and state estimation of six-wheeled mobile robot platforms equipped with articulated suspension (RVAS). He has developed a compact, 3D-printed version of this platform and implemented Kalman filter-based algorithms to accurately estimate vehicle velocity, acceleration, and slip ratio—critical for autonomous navigation on uneven ground. His work on state estimation (2020–2021, 2–4 citations) provides a foundation for robust control in unmanned ground vehicles. Oh’s dual expertise in algorithmic learning and physical system design makes his research particularly valuable for creating intelligent robots that can adapt and move reliably in the real world.