Afef Benjemmaa

Papers

Total Citations

H-Index

About

Afef Benjemmaa is a researcher whose work lies at the intersection of artificial neural networks, control systems, and mobile robotics. Her primary research focus is the development of intelligent, learning-based control architectures for autonomous navigation, specifically addressing the challenge of lane following for mobile robots. Benjemmaa’s major contributions center on the design and optimization of neural network systems that can process visual input and generate real-time steering commands, effectively replacing traditional rule-based control with adaptive, data-driven approaches. Her most cited paper, "Implementations approaches of neural networks lane following system" (2012, 7 citations), explores the practical deployment of these networks, emphasizing their speed, learning capability, and robustness. A complementary study, "Optimum Architecture of Neural Networks lane following system" (2012, 4 citations), investigates the ideal structural configuration of these networks to maximize performance. Together, this body of work demonstrates how neural networks can learn from empirical data to control complex systems, reducing the need for explicit programming. Benjemmaa’s research is particularly notable for its early application of machine learning to real-time robotic control, a field that has since become central to autonomous vehicle development.