Max Robotics — Global Service Robot Directory + US Certification

About

Marija Jegorova is a robotics researcher whose work sits at the intersection of machine learning, robot control, and system identification. Her primary research areas include learning algorithms for real-world robotic tasks, behavioral diversity in robot policies, and dynamic system identification. A key contribution is her work on generating behavioral repertoires using Generative Adversarial Policy Networks, which enables robots to adapt to unexpected changes in their environment or morphology by producing multiple distinct behaviors rather than relying on a single learned policy. This approach, presented at the 2019 IEEE ICDL-EpiRob conference (23 citations), addresses a critical limitation in imitation learning. Jegorova has also advanced dynamic system identification by proposing adversarial generation of informative trajectories, moving beyond traditional single-trajectory optimization to produce richer excitation data for determining robot physical parameters. Her research has accumulated over 50 citations, with her most influential paper exploring how robots can overcome environmental perturbations through diverse behavioral strategies. This work has significant implications for developing more robust, adaptable autonomous systems capable of operating in unstructured real-world environments.