Mohammad Zaki Zadeh

Papers

Total Citations

H-Index

About

Mohammad Zaki Zadeh is a robotics researcher focused on bridging the gap between simulation and real-world robot perception. His primary research areas include robot vision, traversability estimation, and domain adaptation for autonomous mobile robots. Zadeh’s most notable contribution is his work on simulated environments for robot vision experiments, where he identified critical limitations in using synthetic data for training—specifically, that physical parameters like temperature and wear-and-tear prevent direct transfer of simulated images to real-world applications. This insight, published in his most-cited paper (5 citations), has helped shape how researchers approach domain randomization. He also developed an innovative method for indoors traversability estimation using Vision Transformers (ViTs), achieving high accuracy with minimal labeled data—a significant advancement for cost-effective robot navigation. His fine-tuning approach on a custom dataset, detailed in his second most-cited work (4 citations), demonstrates practical applications for mobile robots operating in indoor environments. Zadeh’s work is particularly valuable for researchers seeking to reduce the annotation burden in robotic perception while maintaining robust performance, making him a rising voice in the field of learning-based robotics.