Ulises Davalos-Guzman
Papers
1
Total Citations
8
H-Index
1
About
Ulises Davalos-Guzman is a researcher whose work sits at the intersection of robotics, neural network control, and real-time embedded systems. His primary contributions center on the design and implementation of advanced control architectures for robotic manipulators, with a particular focus on achieving robust performance through hardware-in-the-loop (HIL) validation. His most-cited work, "Design and Implementation of a Real Time Control System for a 2DOF Robot Based on Recurrent High Order Neural Network Using a Hardware in the Loop Architecture" (2021, 8 citations), introduces a novel integration of discrete-time recurrent neural identification with sliding-mode control. This approach demonstrates how neural networks can be deployed in real-time to handle the nonlinear dynamics of a two-degree-of-freedom robot, bridging the gap between theoretical control algorithms and practical, high-performance implementation. By leveraging HIL architectures, Davalos-Guzman provides a replicable framework for testing complex controllers without risk to physical hardware—a significant step for cost-effective robotic development. His work is particularly valuable for students and engineers exploring neural-network-based control in resource-constrained, real-world applications, offering a clear pathway from simulation to deployment.
Research Focus
Key Achievements
Top Papers
- 1