Deep Q-Learning in Robotics: Improvement of Accuracy and Repeatability

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 10; p. 3911
• Main Authors: Sumanas, Marius, Petronis, Algirdas, Bucinskas, Vytautas, Dzedzickis, Andrius, Virzonis, Darius, Morkvenaite-Vilkonciene, Inga
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 21.05.2022; MDPI
• Subjects: Accuracy; Algorithms; Automation; Data mining; deep q-learning; Errors; Experiments; Humans; Industrial robots; Kinematics; Machine Learning; Manufacturing engineering; Methods; Neural networks; Optimization techniques; positioning errors; reinforced learning; robot operating system ROS; Robotics; Robotics - methods; Robotics industry; Robots; Simulation; Technology application; robot operating system ROS; robotics; deep q-learning; reinforced learning; machine learning; positioning errors
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22103911

Recent industrial robotics covers a broad part of the manufacturing spectrum and other human everyday life applications; the performance of these devices has become increasingly important. Positioning accuracy and repeatability, as well as operating speed, are essential in any industrial robotics application. Robot positioning errors are complex due to the extensive combination of their sources and cannot be compensated for using conventional methods. Some robot positioning errors can be compensated for only using machine learning (ML) procedures. Reinforced machine learning increases the robot's positioning accuracy and expands its implementation capabilities. The provided methodology presents an easy and focused approach for industrial in situ robot position adjustment in real-time during production setup or readjustment cases. The scientific value of this approach is a methodology using an ML procedure without huge external datasets for the procedure and extensive computing facilities. This paper presents a deep q-learning algorithm applied to improve the positioning accuracy of an articulated KUKA youBot robot during operation. A significant improvement of the positioning accuracy was achieved approximately after 260 iterations in the online mode and initial simulation of the ML procedure.