New Publication in "Engineering Applications of Artificial Intelligence"

Our new article, "Automated Function Development for Emission Control with Deep Reinforcement Learning," has appeared in the journal “Engineering Applications of Artificial Intelligence”. The paper clears the way for the use of data-driven functions for automated control function development. To demonstrate the methodology, the developed framework is used to automatically learn the complex control of an exhaust gas recirculation valve. This enables cost and time reduction while increasing performance in ECU development.

Title: "Automated function development for emission control with deep reinforcement learning"

Authors: Lucas Koch, Mario Picerno, Kevin Badalian, Sung-Yong Lee, Jakob Andert

Full text: DOI / Download