Andreas Doerr

Papers

Total Citations

H-Index

About

Andreas Doerr is a researcher whose work sits at the intersection of control theory, robotics, and machine learning, with a particular focus on data-efficient methods for automating system design. His key research areas include Inverse Optimal Control (IOC) and model-based policy search. Doerr’s most impactful contribution is in "Direct Loss Minimization Inverse Optimal Control" (2015, 35 citations), where he advanced the IOC framework to enable automated planner tuning from straightforward demonstrations—a technique that has strongly impacted systems engineering, particularly for lower-dimensional navigation planning. He further extended model-based reinforcement learning to practical industrial settings in his work on automatic tuning of multivariate PID controllers (2017). By adapting the PILCO framework, Doerr demonstrated how complex, coupled industrial controllers can be tuned automatically, reducing tedious manual effort. Though his citation counts are modest, his work bridges the gap between theoretical optimal control and real-world application, offering practical tools for engineers. Doerr’s research is notable for its emphasis on direct loss minimization and data efficiency, making his contributions valuable for students and practitioners seeking to automate control system design with minimal human intervention.