Intelligent Perception, Decision-Making and Actuation Technologies for Precision Agrochemical Spraying: Current Advances and Future Perspectives
Abstract
Highlights This review examines intelligent spraying systems across perception, actuation, and multi-platform integration in agriculture. Compares 2D field and 3D orchard spraying systems in sensing, control, and fluid dynamics performance. What are the main findings? Sensing accuracy and actuation performance are affected by environmental variability and dynamic delays in the system. Fluid dynamics, droplet formation, and canopy structure significantly influence deposition uniformity and drift behaviors. What are the implications of the main findings? Integrated CPS and digital twin frameworks are needed to improve coordination between sensing and actuation systems. Future systems should combine multimodal sensing and feedforward control to reduce drift and improve efficiency. Abstract This review summarizes recent advances in intelligent spraying systems for precision agriculture. It focuses on the three interconnected components of perception, decision-making, and actuation, and compares the sensing characteristics of 2D planar field crops and three-dimensional orchard canopies. Particular emphasis is placed on evaluating the target recognition capabilities and physical limitations of machine vision, Light Detection and Ranging (LiDAR), ultrasound, and active fluorescence spectroscopy under complex field conditions. At the actuation level, the dynamic response characteristics of Pulse-Width Modulation (PWM), proportional control valves, and adaptive control algorithms are critically reviewed, revealing the influence mechanism of hydraulic transient phenomena, including water hammer effects induced by high-frequency valve switching, on droplet size distribution (DSD). The review further discusses the coupling effects between Unmanned Aerial Vehicle (UAV) airflow fields, Unmanned Ground Vehicle (UGV) motion disturbances, and spray deposition performance, and summarizes reported improvements in pesticide reduction, water conservation, and drift mitigation. Finally, the potential of cyber–physical systems (CPS) and digital twin-based frameworks for developing adaptive and closed-loop intelligent spraying systems is discussed to provide insights into future all-weather and autonomous agricultural operations.