Evgeny Yudin

Skolkovo Institute of Science and Technology

Papers

Total Citations

H-Index

About

Evgeny Yudin is a robotics researcher whose work sits at the intersection of neural fields, motion planning, and simultaneous localization and mapping (SLAM). His key contributions focus on making autonomous navigation more efficient and practical for mobile robots operating under real-world constraints. Yudin’s most notable work includes NFOMP, a neural field-based optimal motion planner designed specifically for differential drive robots with nonholonomic constraints. This approach overcomes the limitations of classical sampling-based planners by producing smoother, shorter trajectories in reasonable computation time—a critical advance for real-time applications. In SLAM, Yudin developed MeSLAM, a memory-efficient framework that leverages neural fields to address the scalability issues of long-term robot operation, preventing the unbounded growth of map size that plagues traditional methods. He also introduced MuCaSLAM, which uses a CNN-based frame quality assessment layer to improve the robustness and computational efficiency of visual SLAM on multi-camera, resource-constrained platforms. With over 57 citations across these three papers alone, Yudin’s work is gaining traction for its practical, hardware-aware approach to deploying advanced neural techniques on real robots.