Syed Moshfeq Salaken
Papers
4
Total Citations
34
H-Index
4
About
Syed Moshfeq Salaken is a researcher at the forefront of autonomous systems, specializing in deep imitation learning and its application to robotics and autonomous driving. His work addresses a critical challenge in the field: enabling machines to learn complex navigation and control policies directly from expert demonstrations, bypassing the need for hand-coded rules. Salaken’s most influential paper, “Evaluating Architecture Impacts on Deep Imitation Learning Performance for Autonomous Driving” (19 citations), systematically investigates how different deep neural network architectures affect imitation learning outcomes, providing a foundational guide for practitioners. He further advanced the field through comparative studies on transfer learning for autonomous navigation (6 citations) and introduced a novel, camera-only approach to local motion planning for mobile robots (5 citations). Beyond navigation, Salaken has explored human-robot interaction, contributing to the development of an empathy-controlled robot for Industry 5.0 (4 citations). His research consistently pushes the boundaries of end-to-end learning, demonstrating how deep neural networks can transform raw sensory input into robust, real-world driving and robotic behaviors.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4