Autonomous navigation of agricultural machinery has been the fundamental and core pillar in the advancement of precision agriculture. The production efficiency and product quality can be enhanced to simultaneously reduce the resource consumption and environmental footprint. This review aims to systematically examine the research progress in the autonomous navigation technology for agricultural machinery. A particular emphasis was placed on the current state-of-the-art and emerging trends within two critical technological domains: navigation positioning and navigation control. Significant efforts were also made on the navigation positioning. Specifically the high-precision global navigation satellite system (GNSS) (real-time kinematic (RTK) and precise point positioning (PPP)) was delivered the centimeter-level absolution of the positioning accuracy. Concurrently, machine vision approaches provided robust solutions for the centimeter-level relative positioning. Both conventional algorithms and increasingly powerful deep learning techniques were balanced for the feature extraction and scene understanding, along with light detection and ranging (LiDAR) systems. Some limitations were also proposed after the comparison. Single-sensor systems were recognized in the complex, dynamic agricultural environments. The dominant and most effective paradigm emerged as the multi-sensor fusion strategies integrating GNSS, inertial navigation systems (INS), vision, and LiDAR data. This convergence of data streams was essential to enhance system resilience, reliability, and adaptability across diverse and challenging field conditions. In navigation control technologies, solutions were tailored to different machinery classes. Hydraulic steering systems remained the preferred choice for heavy-duty agricultural equipment, due to their high force. While the electric steering systems offered distinct advantages, in terms of precision, responsiveness, and integration ease, increasingly suitable for medium and small-sized machinery. Substantial progress was achieved in the path-tracking algorithms. Some techniques, such as Model Predictive Control (MPC), were used to predict the future states for the optimal control actions. Adaptive Pure Pursuit methods dynamically adjust look-ahead distances for smoother tracking. Intelligent optimization algorithms further enhanced the accuracy and the robustness of path following. Advanced control strategies demonstrated the superior performance, particularly under demanding operating scenarios like steep slopes, uneven terrain, and conditions prone to wheel slip or side-slip. Technological evolution was found in the practical implementation and commercialization. International manufacturers of agricultural machinery, including John Deere and CLAAS, successfully transitioned the high-precision autonomous navigation solutions into the large-scale, commercially viable products widely adopted in modern farming. National enterprises, such as Huace Navigation and Shanghai Lianshi, also deployed navigation systems. BeiDou navigation satellite system (BDS) was also utilized under various agricultural scenarios. Looking ahead, future research should strategically focus on several key directions: The intelligent context-aware fusion for the multi-modal sensor data streams; navigation algorithms optimization specifically for highly specialized agricultural tasks and environmental conditions; and the deeper, more seamless integration of autonomous navigation with the precision agricultural implements and operations. These avenues can be instrumental for agricultural machinery autonomous navigation towards the higher levels of intelligence, broader applicability, and greater practical utility. This trajectory can provide a strong reference to accelerate the modernization and sustainable transformation of global agriculture.

A steering control system is one of the key steps in the tractor's automatic navigation. Many nonlinear factors (such as hydraulic dead zone, saturation zone, and mechanical backlash) can dominate the performance of steering control, even the accuracy and stability of tractor navigation. In this study, the Lovol Europa M704-2H tractor was taken as the test platform with the electric steering wheel instead of the onboard steering wheel as the actuator, where the angle sensor on the steering wheel axle of the tractor to measure the size of the wheel turning angle. The steering control system included the steering angle calibration and the steering control. The steering angle calibration aimed to obtain the limit angle and median AD value size of the tractor, and then the steering wheel angle size at any angle by linear fitting. The limit steering angle calibration was required for the tractor steering wheel close to the limit through a circle, the satellite positioning of the trajectory point, and the least squares, in order to obtain the minimum turning radius of the tractor. The two-wheel model of the tractor was then utilized to calculate the maximum steering angle. The median steering angle calibration was required for the tractor to drive a section of an approximate straight-line trajectory. The least squares method (LSM) was also used to identify the correction of the zero position for the accurate median AD value. The TZ-QX2A6/5T front wheel angle meter was selected to compare the front wheel angle with the sensor measurement. The results show that the maximum error of calibrated angle measurement was 1.3°, and the average error was 0.11°, fully meeting the demand of steering control. At the same time, the mechanical backlash of the steering system was firstly quantified, in terms of the angular size of steering wheel reversal across the free travel. The accurate size of mechanical backlash was obtained through experimental identification. Then, the fuzzy PD steering control with backlash compensation was designed at the same time. When the electric steering wheel was out of the free travel, the fuzzy PD control was adopted; when the electric steering wheel was in free travel, the steering control was compensated to add the backlash P control into the output of the fuzzy PD control. Simulation results in Simulink show that better performance was achieved in the tracking of the steering angle signals of square wave and sinusoidal wave, fully meeting the requirements. The fuzzy PD steering control with/without the backlash compensation was also used to compare the tracking performance of square wave and sinusoidal steering angle signals. The experimental results show that the response time of the square wave angle signal tracking without backlash compensation was 1.3 s, where the maximum and average steady-state errors were 0.672°, and 0.244°, respectively. The average delay time of the sine wave angle signal tracking without backlash compensation was 0.5 s, where the maximum and average errors were 2.59° and 1.32°, respectively. Compared to the algorithm without backlash compensation, the time of steering angle error within ±0.2° was improved by 71%, the maximum steady state error was reduced by 0.022°, and the average steady state absolute error was reduced by 0.112°. Once the backlash compensation was performed, the response time of the square wave angle signal tracking was 1.1 s, where the maximum and average steady-state errors were 0.65°, and 0.132°, respectively. The average delay time of the sine wave angle signal tracking was 0.5 s, the maximum and average errors were 1.91° and 1.09°, respectively. Compared to the algorithm without backlash compensation, the maximum error was reduced by 0.68°, and the average error was reduced by 0.23°. The experimental results show that the backlash compensation outstandingly improved the stability of steering control for the less control error. The linear navigation test on the leveled field showed that the maximum and absolute average errors of angle tracking were 2.82° and 0.61°, respectively, when the system was in a steady state. Therefore, better performance was achieved with the high accuracy of the steering control system.