Jonathan Cepeda–Negrete

Papers

Total Citations

H-Index

About

Jonathan Cepeda–Negrete is a researcher at the forefront of autonomous robotics and computer vision, with a primary focus on humanoid robot navigation and visual localization. His most influential work, "Transfer Learning for Humanoid Robot Appearance-Based Localization in a Visual Map" (2021, 17 citations), addresses a critical challenge in robotics: enabling robots to maintain accurate localization when visual conditions—such as lighting or perspective—change unexpectedly. By applying transfer learning techniques, Cepeda–Negrete demonstrated how humanoid robots can adapt pre-trained neural networks to new environments without requiring exhaustive retraining, significantly improving their robustness in real-world settings. This contribution has been cited by peers working on visual SLAM, deep learning for robotics, and adaptive navigation systems. His research bridges the gap between theoretical machine learning and practical robotic deployment, offering scalable solutions for autonomous agents. Cepeda–Negrete’s work is particularly notable for its emphasis on appearance-based methods, which rely on visual features rather than expensive sensors, making his approaches more accessible for low-cost robotic platforms. As a rising voice in his field, his studies continue to inspire new approaches to lifelong learning and domain adaptation in robotics, with implications for service robots, search-and-rescue operations, and human-robot interaction.