Max Robotics — Global Service Robot Directory + US Certification

About

Martin Asenov is a robotics researcher whose work sits at the intersection of computer vision, system identification, and dynamics modeling. His primary research focus is on extracting physical parameters and dynamical models directly from video data—a capability that enables robots to understand and interact with dynamic environments without requiring specialized sensors. Asenov’s major contribution is the development of the Vid2Param framework, which infers dynamics parameters such as mass, damping, and stiffness from video streams, allowing robots to perform physical reasoning in real time. His most cited paper, "Vid2Param: Modeling of Dynamics Parameters From Video" (2019), has garnered 10 citations and addresses the challenge of locating features and reconstructing dense spatiotemporal fields in resource-constrained settings, such as gas source localization. Asenov also introduced V-SysId (2021), a method that simultaneously discovers 3D keypoints, performs system identification, and calibrates extrinsic camera parameters from unlabeled video using only the equations of motion as weak supervision. This work has significant implications for robotics applications requiring robust perception and control in unstructured environments. Asenov’s research is notable for its practical approach to bridging vision and dynamics, offering scalable solutions for autonomous systems.