Anatoly Onishchenko

Moscow Institute of Physics and Technology

Papers

Total Citations

H-Index

About

Anatoly Onishchenko is a researcher at the forefront of integrating large language models with robotics, focusing on enhancing the adaptability and robustness of autonomous systems. His primary research areas include visual-language model-based replanning, instruction following, and human-robot interaction. Onishchenko’s major contribution is the development of LERa (Look, Explain, Replan), a novel approach that enables robots to detect and recover from execution failures by leveraging visual feedback. Unlike traditional text-only planning systems, LERa allows robots to “see” their environment, explain discrepancies, and dynamically adjust their actions, significantly improving real-world task completion. His work, published in 2025, has already garnered early citations, highlighting its emerging impact on the field. Onishchenko’s research addresses a critical gap in robotic autonomy—bridging the divide between static planning and dynamic environments—making his contributions highly relevant for students and researchers exploring embodied AI. His achievements promise to shape future developments in reliable, visually-aware robotic systems.