Max Robotics — Global Service Robot Directory + US Certification

About

Te Tang is a robotics researcher whose work spans two deeply interconnected domains: robotic assembly automation and deformable object manipulation. His early contributions focused on the longstanding industrial challenge of peg-hole insertion, where he developed autonomous force/torque-based alignment methods and pioneered learning-from-demonstration frameworks that enable robots to acquire human assembly skills without exhaustive manual programming. These works, published around 2015–2016, have collectively garnered over 200 citations, reflecting their practical relevance to industrial automation. Tang's research trajectory then expanded into the formidable problem of manipulating deformable linear objects such as cables and wires — a frontier where infinite-dimensional configuration spaces make real-time tracking and control exceptionally difficult. His unified framework leveraging Coherent Point Drift registration (73 citations) and a structure-preserving point cloud tracker (71 citations) established foundational tools for this field. More recently, his hybrid offline-online graph neural network approach to deformation modeling (62 citations) demonstrates his embrace of data-driven methods for robust robotic control. Across his portfolio, Tang has shown a consistent ability to bridge theoretical rigor with real-world applicability, making him a significant contributor to the advancement of intelligent, adaptable industrial robotics. His body of work totals over 500 citations, underscoring his growing influence in the field.