Dmytro Kuzmenko

National University of Kyiv-Mohyla Academy

Papers

Total Citations

H-Index

About

Dmytro Kuzmenko is a leading researcher at the intersection of computer vision and assistive robotics, dedicated to making human-robot locomotion safer and more intuitive. His primary research areas include egocentric visual perception, deep learning for terrain recognition, and the development of large-scale datasets for prosthetic and exoskeleton control. Kuzmenko’s major contribution is pioneering vision-based systems that allow robotic legs to “see” and anticipate complex walking environments before physical contact. He is the driving force behind the creation of ExoNet and StairNet—the largest open-source image datasets of real-world walking environments. His most cited work, “StairNet: visual recognition of stairs for human–robot locomotion” (2024, 23 citations), demonstrates how egocentric vision can detect stair transitions, a critical challenge for lower-limb assistive devices. By leveraging semi-supervised learning, as shown in his 2023 papers (9 and 6 citations), Kuzmenko has significantly improved the efficiency of convolutional neural networks for this task, reducing reliance on expensive labeled data. His work is foundational for the next generation of intelligent prosthetics and exoskeletons, directly impacting the mobility and quality of life for individuals with lower-limb impairments.