Andrey Gorodetsky
Papers
1
Total Citations
8
H-Index
1
About
Andrey Gorodetsky is a researcher at the forefront of embodied AI and human-robot interaction, with a primary focus on bridging the gap between language understanding and physical action. His most cited work, "Fine-Tuning Multimodal Transformer Models for Generating Actions in Virtual and Real Environments" (2023), introduces RozumFormer—a pioneering bimodal transformer architecture that translates natural language instructions into precise robotic manipulation tasks. This contribution is notable for its novel approach to fine-tuning pre-trained multimodal models for real-world control, demonstrating how language can directly guide agents in both simulated and physical settings. With 8 citations and growing influence, Gorodetsky’s research addresses a critical challenge in robotics: enabling machines to interpret complex commands and execute context-aware actions. His work sits at the intersection of natural language processing, computer vision, and reinforcement learning, offering a scalable pathway toward more intuitive human-robot collaboration. By advancing transformer-based architectures for action generation, Gorodetsky is helping to define how future autonomous systems will understand and interact with their environments, making his research essential reading for students and engineers working in interactive AI and robotics.
Research Focus
Key Achievements
Top Papers
- 1