Oscar Fuentes

Papers

Total Citations

H-Index

About

Oscar Fuentes is a robotics researcher whose work focuses on advancing autonomous navigation through probabilistic models and machine learning. His primary research areas include mobile robot localization, simultaneous localization and mapping (SLAM), and topological map representation. Fuentes is best known for pioneering the use of Hidden Markov Models (HMMs) in robotics, demonstrating how these probabilistic frameworks can simultaneously estimate a robot’s position and orientation—a significant step beyond traditional region-based localization. His most cited paper (2018, 8 citations) introduced this HMM-based map representation, while his subsequent work on a graph SLAM system (2021, 4 citations) fuses multiple sensor readings using a Dual HMM to improve accuracy. Fuentes has also explored evolutionary robotics, using genetic algorithms to generate reactive robot behaviors (2021, 4 citations), and developed Sparse-Map (2022), an unsupervised learning approach that automatically creates topological maps to overcome the memory limitations of dense 2D occupancy grids. Though early in his career, Fuentes’s contributions are carving a niche in efficient, probabilistic robot perception, with his HMM-based methods offering a promising alternative to conventional SLAM techniques.