Sergio Ledesma

Papers

Total Citations

130

H-Index

About

Sergio Ledesma’s research lies at the intersection of computer vision, robotics, and machine learning, with a strong focus on enabling intelligent systems to perceive and navigate their environments. His most impactful work, “Human activity recognition using temporal convolutional neural network architecture” (2021), has garnered 109 citations, demonstrating a significant contribution to the field of human motion analysis. This work leverages deep learning to interpret complex temporal sequences, a key challenge in autonomous systems and human-robot interaction. In robotics, Ledesma has advanced autonomous visual navigation, notably through his 2021 study on “Transfer Learning for Humanoid Robot Appearance-Based Localization in a Visual Map” (17 citations), which addresses the critical task of accurate robot localization using pre-trained neural networks. Earlier in his career, he explored boosting methods for natural image interpretation (2008), applying Adaboost to classify terrain features like roads, trees, and sky—a foundational step toward scene understanding. Ledesma’s research consistently bridges theoretical machine learning with practical robotic applications, making his work valuable for students and researchers developing perception systems for autonomous agents.