The Full-Field Path Tracking of Agricultural Machinery Based on PSO-Enhanced Fuzzy Stanley Model

The unmanned operation of agriculture machinery in the full field farmland is an important part farm and smart agriculture. Although autonomous navigation for robot has been widely studied literature, research on full-field path tracking problem rare. In this paper, order to enhance adaptivity algorithm, improved fuzzy Stanley model (SM) proposed based particle swarm optimization (PSO), where control gain modified adaptively according error, velocity steering actuator saturation. PSO-enhanced SM (PSO-FSM) verified by experiments numerical simulation self-driving mobile vehicle. Simulation results indicate that PSO-FSM achieves a better result than FSM, changes under different velocities saturation conditions, maximum lateral errors vehicle turning are 0. 32 m 0.03 m, respectively. When location deviates from expected at 4 direction, distance guided trajectory reach no more 5 m. A preliminary experiment also carried out wheeled combine harvester working slippery soil, indicates error 0.63 which acceptable with large width.