Robot learning for complex manufacturing process

At the present time, industrial robots for assembly tasks only constitute a small portion of the annual robot sales. One of the main reasons is that it is difficult for conventional industrial robots to adapt to the complicity and flexibility of assembly processes. Therefore, intelligent industrial robotic systems are attracting more and more attention. However, because of the modeling difficulty and low efficiency of the existing solutions, optimal performance is difficult to achieve. In this paper, a parameter learning method is developed based on Gaussian Process Regression Bayesian Optimization Algorithm (GPRBOA). Gaussian Process Regression(GPR) is utilized to model the relationship between the process parameters and system performance. GPRBOA is proposed to optimize the process parameters. The experiments were performed using a complex three stage torque converter assembly process. The experimental results verify the effectiveness of the robot learning method and demonstrate its efficiency compared to Design Of Experiment(DOE) methods. The proposed method can greatly increase the manufacturing efficiency and will generate big economic impact.