An Adaptive Double Closed‐Loop Path Tracking Control Method for High‐Precision Autonomous Navigation of Agricultural Machinery

ABSTRACT To improve the path tracking accuracy and adaptability of agricultural machinery in complex field environments, we proposed a path tracking control method based on a double closed‐loop control that combines an improved pure pursuit algorithm with fuzzyproportional integral derivative (PID) control. The improved pure pursuit algorithm dynamically adjusts the look‐ahead distance according to agricultural machinery speed, path curvature, and position deviation, modeling it as a polynomial function of these variables. Offline simulations under diverse operational conditions were performed, and the ant colony algorithm (ACA) was employed to optimize the polynomial weight parameters, ensuring fast and accurate computation of the look‐ahead distance during autonomous navigation in the field. The computed front‐wheel steering angle is then controlled by a fuzzy PID algorithm, enabling rapid and precise steering adjustments, thereby enhancing the responsiveness and accuracy of path tracking. Field experiments were conducted to evaluate the proposed method. Comparative experiments were performed with standard Pure Pursuit, PID, and Stanley controllers. The results indicate that, compared with these methods, the proposed approach, which adaptively adjusts the look‐ahead distance according to different operating conditions, achieves higher adaptability and superior path tracking accuracy under different conditions. At a speed of 1 m/s, the agricultural machinery achieved a mean path‐tracking error of less than 3.30 cm during straight‐line navigation. For curved paths with turning radii of 4, 7.5, and 10 m, the mean path tracking error remained below 4.50 cm. Furthermore, during full‐field autonomous navigation, the mean path tracking error was under 4.70 cm, demonstrating the proposed method has high adaptability and robustness under varying operating conditions.