Mohammad Rashed
Papers
1
Total Citations
1
H-Index
1
About
Mohammad Rashed is a researcher at the forefront of applied deep learning for autonomous systems, with a primary focus on computer vision and domain adaptation in intralogistics. His work addresses a critical bottleneck in warehouse automation: the performance degradation of Convolutional Neural Networks (CNNs) when deployed in environments different from their training data. Rashed’s most notable contribution is the development of a GAN-based domain adapted deep learning pipeline for object detection in warehouse settings, a pioneering approach that enables Autonomous Mobile Robots (AMRs) to reliably recognize load carriers using vision-based guiding systems. This work, published in 2024, tackles the practical challenge of sim-to-real transfer, where models trained on synthetic or controlled data must perform robustly in dynamic, real-world warehouses. Although early in its citation trajectory, this paper represents a significant step toward bridging the gap between laboratory-trained perception systems and industrial deployment. Rashed’s research is essential reading for students and engineers working on domain adaptation, GANs, and robotics perception, offering a concrete solution to one of the most persistent hurdles in autonomous intralogistics.
Research Focus
Key Achievements
Top Papers
- 1