R. Fematt
Papers
1
Total Citations
8
H-Index
1
About
R. Fematt’s research lies at the intersection of robotics, artificial intelligence, and spatial computing, with a focus on efficient path planning in known environments. Their most cited work, “Path planning in a 2-D known space using neural networks and skeletonization” (2002, 8 citations), introduces a novel hybrid approach that combines Kohonen self-organizing maps with Kwok’s skeletonization method. This technique reduces complex spatial data into a simplified representation, enabling faster and more intelligent navigation for autonomous systems. By integrating neural network learning with geometric skeletonization, Fematt’s contribution offers a computationally efficient alternative to traditional path planning algorithms, particularly valuable for mobile robots operating in structured spaces. Though their citation count is modest, the work demonstrates early adoption of neural methods in robotics, foreshadowing later advances in deep reinforcement learning for navigation. Fematt’s research remains a relevant reference for scholars exploring bio-inspired and topology-based approaches to autonomous motion, highlighting the enduring value of interdisciplinary thinking in robotics and AI.
Research Focus
Key Achievements
Top Papers
- 1