Mariem Boujelbene

Papers

Total Citations

H-Index

About

Mariem Boujelbene is a researcher at the forefront of applying deep learning to robotics, with a particular focus on predictive maintenance and system reliability. Her most cited work, "Robot failure mode prediction with deep learning sequence models" (2024), introduces novel sequence-based architectures that anticipate mechanical and software failures before they occur, significantly advancing the safety and autonomy of robotic systems. By leveraging recurrent and transformer-based models, Boujelbene’s approach enables real-time anomaly detection in complex operational environments, reducing downtime and enhancing long-term deployment viability. Though early in her career, her contributions have already garnered attention, with this paper accumulating 5 citations—a strong indicator of its relevance in the rapidly evolving field of intelligent robotics. Her research bridges the gap between theoretical deep learning and practical robotic resilience, offering scalable solutions for industrial and service robots. Boujelbene’s work is particularly notable for its emphasis on interpretability and efficiency, making it accessible for both academic researchers and industry engineers. As she continues to publish, her focus on failure prediction positions her as a rising authority in safe, autonomous system design.