Kiavash Fathi

ZHAW Zurich University of Applied Sciences

Papers

Total Citations

H-Index

About

Kiavash Fathi is an emerging researcher specializing in intelligent robotics, predictive maintenance, and human-robot interaction — fields sitting at the dynamic intersection of industrial automation and machine learning. His most recognized contribution, "Predictive Maintenance: An Autoencoder Anomaly-Based Approach for a 3 DoF Delta Robot" (2021), has garnered 23 citations and addresses one of the most persistent challenges in industrial systems: performing reliable predictive maintenance without run-to-failure data. By leveraging autoencoder-based anomaly detection, Fathi developed a framework for identifying condition indicators and estimating health indices even when complete failure datasets are unavailable — a practically significant advancement for real-world manufacturing environments. His 2022 work on human-robot contact detection in assembly tasks reflects a forward-thinking engagement with Industry 5.0 principles, tackling the critical safety and perception challenges that arise when humans and robots share collaborative workspaces. Across his growing body of work, Fathi consistently bridges theoretical machine learning techniques with tangible engineering applications, making his research particularly valuable to practitioners in smart manufacturing, robotics engineering, and industrial AI. His trajectory suggests a researcher poised to make increasingly significant contributions as autonomous and collaborative robotic systems become central to modern industry.