Yaroslav Solomentsev

Moscow Institute of Physics and Technology

Papers

Total Citations

H-Index

About

Yaroslav Solomentsev is a leading researcher in autonomous robotics, specializing in deep reinforcement learning, real-time object navigation, and indoor place recognition. His work bridges the gap between advanced neural network architectures and practical robotic deployment, addressing critical challenges in computational efficiency and environmental perception. Solomentsev’s most cited paper, “Real-Time Object Navigation With Deep Neural Networks and Hierarchical Reinforcement Learning” (2020, 51 citations), introduces a hierarchical framework that enables mobile robots to navigate complex environments with limited onboard processing, significantly improving real-world applicability. This contribution has been widely recognized for its impact on autonomous systems, particularly in integrating deep learning with reinforcement learning for dynamic navigation tasks. More recently, his paper “HPointLoc: Point-Based Indoor Place Recognition Using Synthetic RGB-D Images” (2023, 11 citations) presents an innovative approach to robust place recognition using synthetic data, reducing reliance on costly real-world datasets. Solomentsev’s work is notable for its practical focus on real-time performance and scalability, making him a key figure in advancing mobile robotics. His research continues to inspire new methods for efficient, intelligent navigation in unstructured environments.