Elizaveta Pestova

Skolkovo Institute of Science and Technology

Papers

Total Citations

H-Index

About

Elizaveta Pestova is a robotics researcher whose work centers on advancing quadruped locomotion through the integration of machine learning and real-to-sim transfer techniques. Her key contributions lie in developing systems that enable legged robots to perceive and adapt to diverse terrains, bridging the gap between physical hardware and simulated environments. In her highly cited 2024 paper, "HyperSurf: Quadruped Robot Leg Capable of Surface Recognition with GRU and Real-to-Sim Transferring," Pestova introduces a novel mechanical single-leg setup designed for rapid data collection across interchangeable surfaces. This system employs a Gated Recurrent Unit (GRU)-based surface recognition model, allowing the robot to identify and respond to different ground types with remarkable accuracy. By pioneering a real-to-sim transferring pipeline, she has significantly enhanced the efficiency of training locomotion controllers, reducing the need for extensive physical trials. With 2 citations already, this work is gaining traction for its practical approach to improving robot adaptability. Pestova’s research is particularly impactful for students and engineers interested in the intersection of robotics, deep learning, and simulation, offering a scalable framework for developing more intelligent and resilient legged robots.