Fatemeh Kakavandi
Papers
3
Total Citations
78
H-Index
2
About
Fatemeh Kakavandi’s research sits at the intersection of advanced manufacturing and intelligent robotics, with a primary focus on digital twin technologies and humanoid robot control. Her most impactful work, “A review of unit level digital twin applications in the manufacturing industry,” has garnered 74 citations, establishing her as a key voice in the integration of virtual replicas for real-time production monitoring and optimization. In robotics, Kakavandi has made notable contributions to humanoid stability, developing a learning-based approach for push recovery in the NAO robot. Her method leverages force-sensitive resistor data to enable dynamic balance, allowing robots to recover from disturbances and perform imitation tasks more reliably—a critical step toward deploying humanoids in unstructured environments. More recently, she has ventured into explainable AI for quality assurance, as demonstrated in her work on a medical device assembly pilot line. By addressing the “black box” nature of deep learning models, she has proposed interpretable frameworks that enhance trust and transparency in sensitive pharmaceutical processes. Through these contributions, Kakavandi bridges the gap between theoretical AI and practical industrial applications, making her research valuable for both manufacturing engineers and robotics researchers.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3