Max Robotics — Global Service Robot Directory + US Certification

About

Daniel Kubus is a robotics researcher whose work spans manipulation control, sensor fusion, human-robot interaction, and robot programming. His most influential contribution, "On-line estimation of inertial parameters using a recursive total least-squares approach" (2008, 64 citations), introduced a robust method for estimating the inertial properties of loads attached to robotic manipulators — a foundational advance enabling more accurate force control, object recognition, and pose estimation. Complementing this, his early work on fusing six-dimensional force/torque and acceleration signals laid critical groundwork for compliant manipulation, appearing across multiple publications and accumulating nearly 40 combined citations. Kubus has also made meaningful contributions to intuitive robot programming, exploring kinesthetic teaching, tactile surface sensors as gesture-based interfaces, and visual-inertial fusion for bin-picking and grasping tasks. His 2018 work on continuously shaping projection operators addressed a long-standing challenge in multi-objective robot control. Beyond manipulation, he contributed to medical robotics through a prototype for robot-assisted endoscopic sinus surgery and investigated high-update-rate bilateral teleoperation systems. Across his career, Kubus consistently bridges theoretical rigor with practical application, making his research particularly relevant to those working at the intersection of industrial automation and human-robot collaboration.