Reinforcement learning for robotic assembly of fuel cell turbocharger parts with tight tolerances

Abstract

The efficiency of a fuel cell is not only dependent on the stack, but also to a large extent on the turbocharger, which is responsible for providing the required airflow. Since the individual components, especially those of the rotor, are subject to high demands on manufacturing accuracy, it is crucial to ensure a precise and robust assembly. In order to achieve a scalable assembly process, this paper presents a method for a robot-based assembly of the rotationally symmetric components of the rotor. The assembly task has been reduced to the two essential problems: search and insertion. On this basis, a system was developed, which is able to learn the joining process independently and compensate for positioning inaccuracies with the help of reinforcement learning in combination with a position-controlled robot. The applied reinforcement learning strategy is based on the measurement data of a 6-axis force/torque sensor, with which the current contact state can be evaluated and a decision for the next step can be made. The experimental verification shows that an automation of the assembly process is possible with the proposed strategy. The robot is able to perform the search operation successfully, whereas limitations to the achievable accuracies of the insertion process could be found.

Hole-Finding Learning Strategy for a Robot Assembly With Keyed Circular Peg

“…A peg-hole data model uses machine learning methods to train contact state data offline and predict the current state online [13][14][15]. This model is updated in real time for online learning through data input from the current contact state [16][17][18][19][20]. Both online and offline data modeling are affected by large data quantities and the complexity of reverting model errors.…”