Mario Michael Krell

University of Bremen, University of California, Berkeley

Papers

Total Citations

H-Index

About

Mario Michael Krell's research sits at the intersection of neuroscience, machine learning, and robotics, with a focus on creating more intuitive human-machine interfaces. His most cited work, "On the Applicability of Brain Reading for Predictive Human-Machine Interfaces in Robotics" (2013, 37 citations), explores how brain signals can be decoded to anticipate human intentions, enabling robots to proactively assist in daily tasks—a foundational step toward truly collaborative robotics. Krell further advances robotic autonomy through machine learning, as demonstrated in "Learning magnetic field distortion compensation for robotic systems" (2017, 13 citations), where he applies neural networks and support vector regression to correct sensor inaccuracies caused by magnetic interference, improving the reliability of inertial measurement units in dynamic environments. His work "Accounting for Task-Difficulty in Active Multi-Task Robot Control Learning" (2015, 5 citations) introduces adaptive learning strategies that consider task complexity, allowing robots to prioritize and allocate resources efficiently. By bridging cognitive state estimation with robust sensor processing, Krell’s contributions enhance both the perceptive and predictive capabilities of robotic systems, laying groundwork for safer, more responsive human-robot interaction in real-world settings.