Skip to Content
You are currently on the new version of our website. Access the old version .
SensorsSensors
  • Review
  • Open Access

26 August 2026

37 Pages

Intelligent Perception, Decision-Making and Actuation Technologies for Precision Agrochemical Spraying: Current Advances and Future Perspectives

,
,
,
and
1
School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China
2
School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China
*
Author to whom correspondence should be addressed.

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.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.