Papers
6
Total Citations
19
H-Index
3
About
Saifeddine Aloui is a robotics researcher whose work lies at the intersection of tactile sensing, dexterous manipulation, and data-driven grasp planning. His major contributions include developing a spectro-temporal recurrent neural network that fuses FFT-based spectral analysis with GRU deep learning to detect slippage in robotic manipulation using a single piezoelectric tactile sensor—a method that improves both efficiency and adaptability. Aloui has also pioneered grasp space exploration for underactuated grippers, introducing a human-initiated approach combined with variational autoencoders to model and generate reliable grasps from limited manual datasets. His earlier work on intrinsic tactile sensing systems, including a matrix of 3-axis force sensors capable of measuring force, torque, and centroid position, laid the foundation for achieving the sensory feedback necessary for true dexterous manipulation. With each of his most-cited papers accumulating 2–4 citations, Aloui’s research is steadily gaining recognition for its practical, data-driven solutions to longstanding challenges in robotic grasping and tactile feedback—making his work essential reading for students and researchers advancing autonomous manipulation.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6Intrinsic tactile sensing system design for robotics manipulation2 citations · 2016