Abstract: The control of the contact force between the tool and the workpiece is particularly important in the robot's automated polishing and grinding process. Based on the principle of active compliance control, this paper proposes a compliance force control device and control method for industrial robots. The structural design and dynamic modeling of the system are carried out. Based on the BP neural network PID algorithm, the adaptive control strategy of the compliant force control device is designed. Finally, the force control tracking experiment is carried out. The experimental results show that the compliance force control device can ensure the constant contact force between the workpiece and the tool during the grinding process, thereby improving the surface processing quality.