FPGA Implementation of Family Service Robot Based on Neural Network PID Motion Control System

For the fixed invariability of control parameters in the PID closed-loop control algorithm of existing mobile robot, and the poor real-time response and stability of robot chassis to the upper machine motion control command, a robot motion control system is designed based on BP neural network PID motion control algorithm. Firstly, according to the three-wheel omni-directional mobile robot motion characteristics and the principle of neural network PID control algorithm, the control system is modeled and simulated on simulink, it theoretically demonstrates that the BP neural network PID closed-loop control algorithm is superior to the traditional PID control algorithm. The simulation results show that the overshoot is small and the real-time performance is good, which can greatly improve the flexibility and stability of the system. Then, through the top-down design method by Verilog language, the FPGA design of BP neural network PID closed-loop control system is carried out. The three-wheel omni-directional mobile robot chassis is used as the experimental platform, which is controlled by the robot upper machine to follow and avoid obstacles. The test results show that the control system improves the robot's running speed by 11.6% and accuracy by 13.4%. Compared with the open-loop control system, which effectively verifies the feasibility and practicability of the closed-loop control system.