Max Robotics — Global Service Robot Directory + US Certification

About

Johannes Teutsch is a rising figure in control theory, whose work sits at the intersection of robust and stochastic Model Predictive Control (MPC). His research is driven by a fundamental engineering challenge: how to make long-horizon predictions computationally tractable without sacrificing performance or safety. In his most cited work, "Combined Robust and Stochastic Model Predictive Control for Models of Different Granularity" (2020, 10 citations), Teutsch introduced a novel framework that leverages models of varying fidelity to balance computational cost against control accuracy. This approach enables more efficient handling of uncertainty over extended prediction horizons. He further advanced the field with "Probabilistic model predictive control for extended prediction horizons" (2021, 3 citations), extending these methods to probabilistic settings. Demonstrating versatility, Teutsch has also explored data-driven control, proposing an online adaptation strategy for direct data-driven methods in 2023, and tackled constraint trajectory planning for redundant space robots—a domain with direct applications in aerospace. Though early in his career, Teutsch’s contributions are already shaping the next generation of MPC, offering practical solutions for complex, real-world systems where long predictions are essential.