Max Robotics — Global Service Robot Directory + US Certification

About

Chek Sing Teo is a researcher whose work bridges precision motion control, robotic manipulation, and machine learning, with a particular focus on developing intelligent, data-driven solutions for complex automation challenges. His research spans two complementary domains: advanced control systems for high-precision mechatronic platforms and learning-based methods for robotic perception and grasping. Among his most impactful contributions is his data-driven multiobjective controller optimization framework for magnetically levitated nanopositioning systems (2020, 53 citations), which addresses the longstanding limitations of model-based control by eliminating the need for precise dynamic modeling. This work reflects a broader theme in his research — using machine learning to overcome the bottlenecks of traditional engineering approaches, as further demonstrated in his learning-based high-precision tracking control for flexure-based nanopositioners (2024). In robotics, Teo has made notable strides in robotic grasping and object detection, developing uncertainty-aware domain adaptation networks for grasping detection (30 citations) and a weight-imprinting classification framework enabling variable-stiffness grippers to handle diverse objects universally (22 citations). His incremental few-shot learning work further advances robots' ability to recognize new objects with minimal training data. Spanning two decades of research, Teo's portfolio demonstrates a sustained commitment to pushing the boundaries of precision and intelligence in robotics and automation.