Jonathan Styrud

Jonathan Styrud is a Researcher and Industrial Doctoral Student at the Division of Robotics, Perception, and Learning (RPL) at KTH Royal Institute of Technology, collaborating with ABB Robotics. His research focuses on developing control architectures for industrial robots using reinforcement learning techniques, particularly Behavior Trees, to automate assembly tasks in dynamic environments.

His work is supported by the Wallenberg AI, Autonomous Systems and Software Program (WASP-AI/MLX). He supervises master's theses, such as one exploring methods to avoid local minima in Genetic Programming of Behavior Trees. Notable contributions include investigating hybrid approaches between automated planning and machine learning to enhance robotic adaptability in unstructured settings.

Research interests emphasize bridging the gap between simulation and real-world robot deployment, with a focus on transparency and modularity in control systems. His master's thesis proposal advocates for empirical evaluations of local minima mitigation techniques in robotic manipulation tasks, aiming to improve the efficiency of Genetic Programming.

Academic supervision includes guiding projects on optimization algorithms for Behavior Trees, as detailed in his proposed master's thesis. Current affiliations include RPL at KTH and ABB Robotics, fostering industry-academia collaboration.