Anti-disturbance predictive control for path tracking of unmanned agricultural vehicles based on safety distance

To enhance the path tracking performance of unmanned agricultural vehicles in complex working scenarios with multiple obstacles, this paper proposes an anti-disturbance predictive control scheme based on safe distance. This control scheme leverages the autonomous learning capabilities of predictive control to achieve efficient obstacle avoidance maneuvers for unmanned agricultural vehicles in complex operational scenarios through interaction with the working environment. Initially, an extended state observer is designed to accurately estimate the unknown disturbance within the agricultural vehicle system and incorporate it into the nonlinear predictive model, thereby improving the precision of state prediction and disturbance rejection in the path tracking control system. Subsequently, an automatic optimization algorithm for the reference point of the agricultural vehicle is designed to prevent excessive steering during path tracking. Then, a novel obstacle avoidance penalty term is constructed based on logarithmic function scaling to ensure that the agricultural vehicle maintains a preset safe distance from multiple obstacles during path tracking. Building on this, the cost function is integrated with lateral offset and heading offset information, combined with the obstacle avoidance penalty function, and an anti-disturbance model predictive control scheme is constructed by solving the nonlinear constrained optimization problem online. Simulation results demonstrate that the control scheme proposed in this paper has superior path tracking accuracy and can effectively avoid obstacles while adapting to different safe distance settings and obstacle positions.