Max Robotics — Global Service Robot Directory + US Certification

About

Miguel de la Iglesia Valls is a robotics researcher whose work sits at the intersection of reinforcement learning, model predictive control (MPC), and autonomous navigation. His major contributions center on making complex control systems practical for real-world robots—from legged machines climbing stairs to racecars hurtling around tracks at the limit of traction. His most cited work, "Reinforcement Learning for Blind Stair Climbing with Legged and Wheeled-Legged Robots" (2024, 22 citations), tackles a critical challenge in mobile robotics: enabling robots to autonomously navigate stairs without vision, a capability essential for deployment in human-centric environments. He also pioneered a practical approach to reinforcement learning for MPC, demonstrating that robots can learn effective control policies from sparse objectives in under an hour on real hardware (2020, 14 citations)—a breakthrough that reduces the need for expert tuning. Earlier, as part of the AMZ Driverless team, he contributed to the full autonomous racing system (2020, 11 citations) that powered a racecar to navigate unknown tracks at high speeds. Valls’s work bridges theory and practice, showing that advanced control methods can be deployed efficiently on physical systems. His research is a must-read for anyone interested in making robots more capable, autonomous, and deployable in the real world.