Ilya Belkin

Moscow Institute of Physics and Technology, Integra (Russia)

Papers

Total Citations

100

H-Index

About

Ilya Belkin is a robotics researcher whose work focuses on bridging the gap between advanced AI and real-world mobile robot autonomy. His primary research areas include deep reinforcement learning for navigation, LiDAR-based localization, and multi-sensor fusion for robotic perception in human-oriented environments. Belkin’s most cited work, “Real-Time Object Navigation With Deep Neural Networks and Hierarchical Reinforcement Learning” (2020, 51 citations), addresses the critical challenge of deploying computationally efficient neural networks on physical robots, proposing a hierarchical framework that enables real-time decision-making. He further advanced outdoor robot localization with his 2021 paper on LiDAR-based SLAM (38 citations), which emphasizes modular, lighting-independent positioning systems. His more recent contributions, including a novel method for localizing a robot in a prior 3D LiDAR map using stereo images (2024, 6 citations), demonstrate his commitment to combining classical computer vision with modern neural networks. Belkin’s 2024 work on intelligent control for robotic manipulators in human-centered spaces (5 citations) rounds out a portfolio that consistently tackles the practical deployment of autonomous systems, making his research valuable for students and engineers working on field robotics and embodied AI.