Emmanuel Ovalle-Magallanes

Papers

Total Citations

H-Index

About

Emmanuel Ovalle-Magallanes is a researcher at the forefront of autonomous robotics and computer vision, specializing in deep learning-driven visual navigation. His work centers on enabling mobile and humanoid robots to perceive, map, and localize themselves within their environments using only visual input—a critical step toward truly autonomous locomotion. His most cited paper (2021, 17 citations) introduced a transfer learning framework for humanoid robot appearance-based localization within a visual map, demonstrating how pre-trained neural networks can be adapted to extract robust features for real-time navigation without exhaustive retraining. Building on this, his 2023 work (5 citations) proposed a novel deep learning-based method for generating compact, informative visual maps, directly addressing the challenge of modeling complex environments for efficient localization, planning, and navigation. By integrating transfer learning and generative approaches, Ovalle-Magallanes has advanced the practicality of vision-only navigation systems, reducing reliance on expensive sensors. His contributions are particularly notable for bridging the gap between deep learning theory and real-world robotic deployment, offering scalable solutions for autonomous systems in unstructured settings.