Michal Drozdzal

Papers

Total Citations

H-Index

About

Michal Drozdzal is a leading researcher at the intersection of computer vision, robotics, and multimodal perception. His work fundamentally explores how machines can integrate disparate sensory inputs—particularly vision and touch—to achieve more robust and human-like understanding of the physical world. His highly cited 2020 paper, "3D Shape Reconstruction from Vision and Touch" (25 citations), pioneered the fusion of tactile and visual data for 3D shape reconstruction, demonstrating that combining high-fidelity local touch signals with global visual context dramatically improves object understanding. This work laid the groundwork for a new generation of embodied AI systems. More recently, Drozdzal has been at the forefront of integrating large language models (LLMs) into robotic control loops. His 2024 paper, "InCoRo: In-Context Learning for Robotics Control with Feedback Loops" (2 citations), introduces a novel framework that leverages in-context learning to enable robots to reason and adapt to dynamic environments without explicit retraining. By bridging the gap between high-level reasoning and low-level motor control, Drozdzal’s research is shaping the future of autonomous systems that can learn and interact with the world as intuitively as humans do.