Shahriar Najand
Papers
1
Total Citations
12
H-Index
1
About
Shahriar Najand is a pioneer in the intersection of neural computation and autonomous robotics, with foundational contributions to self-organizing systems and mobile robot navigation. His most-cited work, "Application of Self-Organizing Neural Networks for Mobile Robot Environment Learning" (1993), introduced a novel approach for enabling robots to autonomously map and learn from their surroundings using unsupervised learning algorithms. This early research laid critical groundwork for adaptive robotic perception and spatial cognition, demonstrating how neural networks could replace pre-programmed rules with emergent, data-driven behavior. While his citation count (12) reflects the niche, foundational nature of his work, its influence extends into modern fields like simultaneous localization and mapping (SLAM) and bio-inspired robotics. Najand’s research is notable for its foresight in applying self-organizing maps—a concept later popularized by Teuvo Kohonen—to real-world robotic challenges at a time when neural networks were still emerging from academic obscurity. His work remains a touchstone for engineers exploring unsupervised learning in embodied agents, highlighting the enduring value of early, principled experimentation in AI and robotics.
Research Focus
Key Achievements
Top Papers
- 1