Industrial robots have been applied in labor-intensive and high-risk jobs such as grinding, polishing, deburring, etc. However, traditional robotic manufacturing systems require skillful experts to advise the robot programming for controlling manufacturing efficiency and quality. Based on the level of automation, an advanced cyber-physical robot grinding system has been developed to increase efficiency, improve quality, and save human effort. The proposed system consists of robot trajectory generation and optimization, force-based trajectory modification, vision-based grinding machine localization, and acoustic emission based abrasive belt wear-life analysis. Compared with traditional robot tuning processes, the process quality of the proposed system is better than that, and the tuning time is shortened from 14 days to 1-2 days.