Machine control based on automated learning of subordinate control skills

• Main Authors: Mosandl, Judith, Hein, Daniel, Weber, Marc Christian, Udluft, Steffen
• Format: Patent
• Language: English
• Published: 30.07.2024
• Subjects: AIR INTAKES FOR JET-PROPULSION PLANTS; BLASTING; COMBUSTION ENGINES; CONTROL OR REGULATING SYSTEMS IN GENERAL; CONTROLLING; CONTROLLING FUEL SUPPLY IN AIR-BREATHING JET-PROPULSION PLANTS; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; GAS-TURBINE PLANTS; HEATING; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS; LIGHTING; MECHANICAL ENGINEERING; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS; PHYSICS; REGULATING; WEAPONS

Method and device for controlling a machine in accordance with to multiple control objectives in which machine control is based on automated learning of subordinate control skills, wherein the device provides multiple subordinate control skills which are each assigned to a different one of the multiple control objectives, the device provides multiple learning processes that are reinforcement learning processes that are each assigned to a different one of the multiple control objectives and are configured to optimize the corresponding subordinate control skill based on input data received from the machine, and where the device is configured to determine a superordinate control skill based on the subordinate control skills and to control the machine based on the superordinate control skill.