Antonio Rios Navarro

Papers

Total Citations

H-Index

About

Antonio Rios Navarro is a pioneering researcher at the intersection of robotics, reconfigurable computing, and real-time control systems. His work focuses on overcoming the computational bottlenecks that limit advanced control algorithms in autonomous systems, particularly through the use of Field-Programmable Gate Arrays (FPGAs) for hardware-accelerated neural control. His most-cited paper, "FPGA Hardware Neural Control of CartPole and F1TENTH Race Car" (2025), demonstrates how inexpensive embedded FPGAs can replicate the performance of Nonlinear Model Predictive Control (NMPC) with drastically reduced latency and computational cost. By training neural controllers through supervised learning to mimic NMPC, Navarro has opened new pathways for deploying sophisticated control strategies in resource-constrained robotic platforms—from balancing inverted pendulums to high-speed autonomous racing. His work bridges the gap between theoretical control methods and practical real-time deployment, achieving single-digit millisecond inference times on low-power hardware. With growing recognition in the embedded systems and robotics communities, Navarro’s contributions are shaping the future of agile, intelligent autonomous systems that can operate at the edge without sacrificing performance.