Design and Implementation of Robot Navigation System Based on Neural Network and FPGA

How to achieve autonomous navigation and attitude control for robots in uncertain environments has always been a hot research topic. This study designs an autonomous navigation closed-loop control algorithm based on artificial neural networks and implements a navigation control system for a hexapod robot with field programmable gate array (FPGA). This algorithm includes two aspects: one is the application of fuzzy control theory for fuzzy inference, and the other is autonomous learning and training through convolutional neural networks to optimize the parameters of the closed-loop control algorithm. Finally, an embedded simulation control system was composed of four modules: instruction input, fuzzy control, instruction execution, and closed-loop feedback control. The control system was applied to the autonomous navigation control of a hexapod biomimetic robot, and system testing was conducted. The test results show that the algorithm achieves flexible control of a single steering gear and coordinated control of multiple steering gears, making the robot walking based on this navigation system more stable and improving navigation performance significantly.