Orchard mobile robots (OMR) represent a critical research focus in the field of modern intelligent agricultural equipment, offering the potential to significantly enhance operational efficiency through the integration of path planning and tracking control navigation methods. However, the inherent complexity of orchard environments presents substantial challenges for robotic systems. Researchers have extensively investigated the robustness of various path planning and tracking control techniques for OMR in complex scenes, aiming to improve the robots’ security, stability, efficiency, and adaptability. This paper provides a comprehensive review of the state-of-the-art path planning and tracking control strategies for OMR in such environments. First, it discusses the advances in both global and local path planning methods designed for OMR navigating through complex orchard scenes. Second, it examines tracking control approaches in the context of different motion models, with an emphasis on the application characteristics and current trends in various scene types. Finally, the paper highlights the technical challenges faced by OMR in autonomous tasks within these complex environments and emphasizes the need for further research into navigation technologies that integrate artificial intelligence with end-to-end control systems. This fusion is identified as a promising direction for achieving efficient autonomous operations in orchard environments.

With the advancement of precision agriculture, the autonomous navigation of unmanned agricultural ground vehicles (UAGVs) has emerged as a critical research topic. As a fundamental component of autonomous navigation, path-tracking control is essential for ensuring the accurate and stable operation of UAGVs. However, achieving high-precision and robust tracking in agricultural environments remains challenging due to unstructured terrain, variable wheel slip, and complex dynamic disturbances. This review provides a structured and comprehensive survey of modeling and control methodologies for UAGVs, with particular emphasis on control-theoretic formulations and their applicability across diverse agricultural scenarios. In contrast to prior reviews, the modeling approaches are systematically classified into geometric, kinematic, and dynamic models, including extended formulations that incorporate wheel slip and external disturbances. Furthermore, this paper systematically reviews commonly adopted path-tracking strategies for UAGVs, including proportional–integral–derivative (PID) control, pure pursuit (PP), Stanley control, sliding mode control (SMC), model predictive control (MPC), and learning-based approaches. Emphasis is placed on their theoretical underpinnings, tracking accuracy, adaptability to unstructured field environments, and computational efficiency. In addition, several key technical challenges are identified, such as terrain-adaptive vehicle modeling, slip compensation mechanisms, real-time implementation under hardware constraints, and the cooperative control of multiple UAGVs operating in dynamic agricultural scenarios. By presenting a detailed review from a control-centric perspective, this study aims to serve as a valuable reference for researchers and practitioners developing intelligent agricultural vehicle systems.