A deburring system using the joint of revolute robot manipulator with a tool holder was developed for deburring automation. The tool holder composed of the plunger with spring was developed for freedom of three degree operation. The tool holder was applied for compensation of position errors during trajectory tracing or deburring the workpiece of ununiform. To reduce interacting forces between the high stiffness tool at the end effecter and the workpiece during deburring operation, it was developed to operate flexibly to the direction of tangent line on the revolute axis and to the direction of axis. In this paper, using the deburring system attached at the revolute robot manipulator, deburring experiments were performed. According to the experimental results, the good performance of the proposed deburring system using the revolute robot manipulator was shown.

This study presents intelligent deburring system which can transfer the exper's skill to deburring robot through neural network. The expert's skill is expressed as associate mapping between the characteristics of the burr and human expert's action. Under the fundamental idea that the state of the deburring process can be extracted via the visual sense of the human, we employ vision system for the perception and identification of the changing burr. From the demonstration of human experts, force data are measured and fitted impedance model. Finally the characteristics of the burr and coressponding force are associated by the neural network which is trained through many demonstrations. The proposed method is verified in the deburring process of welding burr.