ABSTRACT Control systems for the navigation of autonomous agricultural robots—particularly those operating in uneven terrain and in the presence of static or dynamic obstacles—have advanced considerably in recent years. As conventional machinery evolves toward increasingly automated systems, the design of reliable navigation controllers has become central to improving field efficiency and reducing operational risks. This review provides a systematic analysis of control strategies implemented in real agricultural environments over the past 11 years, examining how robotic platforms integrate perception, traction, steering, and actuation to follow trajectories and execute tasks in semi‐structured or fully unstructured terrain. Data from 36 robots (eight commercial and twenty‐eight research prototypes) were examined, along with 29 navigation control strategies, implemented in different combinations across the platforms. The findings show a predominance of model predictive control (MPC), proportional‐integral‐derivative (PID), and pure pursuit control (PPC), reflecting their suitability for regulating wheel actuation, maintaining trajectory precision, and handling variable terrain conditions. Less common approaches—such as sliding mode control, linear quadratic regulation, fuzzy controllers, and reinforcement learning—highlight emerging opportunities rather than established practices. Overall, the review underscores the importance of selecting control strategies consistent with robot morphology, sensor configurations, and task requirements, and identifies the need for standardized evaluation metrics (e.g., tracking errors m) and more diverse field testing across crop cycles. These insights help guide future development of robust, scalable navigation systems for autonomous agricultural robots.
Polania et al. (Mon,) studied this question.